- Replace problematic lazy import pattern with direct imports
- Fix 'NoneType' object has no attribute 'conversation_id' error
- Update imports in saas_app_conversation_info_injector.py and related files
- Simplify test file by removing patch workaround
- All imports now work correctly and linting passes
Co-authored-by: openhands <openhands@all-hands.dev>
- Fixed session_maker mocking by directly patching the module-level variable
- Updated all failing tests to properly mock the database session
- Fixed TestUpdateConversationMetadata tests to use correct session_maker
- Fixed TestOnWrite::test_on_write_metadata_success to use correct session_maker
- Fixed TestProcessBatchOperationsBackground tests to use correct session_maker
- All 33 tests in test_event_webhook.py now pass
The main issue was that session_maker is imported directly from storage.database
at module import time, so patching 'storage.database.session_maker' wasn't
effective. Instead, we now directly patch the module-level variable in the
conversation_callback_utils module.
Co-authored-by: openhands <openhands@all-hands.dev>
- Fixed NoneType errors in conversation store, SQL app conversation info service,
conversation callback processor, and event webhook tests
- Added proper mocking of StoredConversationMetadata lazy import to use actual
OpenHands core class instead of None
- Fixed UserStore.get_user_by_id mocking in conversation store tests
- All previously failing tests now pass (23 tests verified)
Co-authored-by: openhands <openhands@all-hands.dev>
The circular import was caused by openhands.events.serialization.event
importing openhands.llm.metrics at module level, which eventually led
back to openhands.events through the config system.
Changes:
- Remove module-level import of openhands.llm.metrics classes
- Add lazy import in event_from_dict function where metrics are used
- Preserve all existing functionality while breaking the import cycle
This fixes the second circular import in the chain:
events.serialization.event → llm.metrics → config → storage → events
Co-authored-by: openhands <openhands@all-hands.dev>
The circular import was caused by openhands.events.event importing
openhands.llm.metrics at module level, which eventually led back to
openhands.events.event through the config system.
Changes:
- Move Metrics import to TYPE_CHECKING block for type annotations
- Add lazy import in llm_metrics property getter for runtime usage
- Use forward references in type annotations
- Preserve all existing functionality while breaking the import cycle
Fixes the ImportError: cannot import name 'Event' from partially
initialized module 'openhands.events.event' error.
Co-authored-by: openhands <openhands@all-hands.dev>
- Created new module openhands/events/recall_type.py with RecallType enum
- Removed RecallType from openhands/events/event.py to break circular dependency
- Updated all import statements across 13 files to use new module path
- Resolves circular import chain: sync/enrich_user_interaction_data.py ->
integrations.github.data_collector -> ... -> openhands.events.event ->
openhands.llm.metrics -> ... -> storage.conversation_callback ->
openhands.events.observation.agent -> openhands.events.event (circular)
The RecallType enum now has minimal dependencies and can be imported
without triggering the heavy dependency chain that caused the circular import.
Co-authored-by: openhands <openhands@all-hands.dev>
- Updated test database schema to include all required tables (user, org, org_member, role, stripe_customer)
- Fixed test fixtures to use unified Base and create proper table relationships
- Updated test mocking to properly handle call_sync_from_async calls in find_customer_id_by_user_id and find_or_create_customer_by_user_id methods
- All tests now pass successfully after the stripe_service.py changes
Co-authored-by: openhands <openhands@all-hands.dev>
- Added mock for User query in save_app_conversation_info() method
- Mock returns a User object with user_id and org_id the same as user_id_uuid
- Handles both UUID formats (with and without dashes) from SQLAlchemy compilation
- Allows other database queries to pass through normally
- Fixes AssertionError in test_user_isolation test
Co-authored-by: openhands <openhands@all-hands.dev>
- Updated ApiKeyStore tests to mock UserStore.get_user_by_id calls
- Added mock_user fixture with current_org_id for org filtering
- Updated SaasSecretsStore tests to mock UserStore calls and handle org_id filtering
- Added tests for retrieve_mcp_api_key functionality
- All tests now properly handle the new org_id-based filtering introduced in commit 69186bc6c
Co-authored-by: openhands <openhands@all-hands.dev>
- Created test_lite_llm_manager.py with 24 test cases covering all methods
- Tests include create_entries, migrate_entries, and update_team_and_users_budget
- Comprehensive coverage of private HTTP client methods (_create_team, _get_team, etc.)
- Tests for public wrapper methods with HTTP client injection
- Error handling scenarios including missing configuration and API failures
- Mock-based testing to avoid external dependencies
- All tests passing with proper fixtures and async support
Co-authored-by: openhands <openhands@all-hands.dev>
- Created new test file enterprise/tests/unit/storage/test_saas_sql_app_conversation_info_service.py
- Added comprehensive test suite for SaasSQLAppConversationInfoService with 4 tests:
* test_service_initialization: Verifies proper service initialization
* test_user_context_isolation: Tests user context isolation between different service instances
* test_secure_select_includes_user_filtering: Validates _secure_select method functionality
* test_to_info_with_user_id_functionality: Tests user_id override from SAAS metadata
- Moved test_user_isolation from TestSQLAppConversationInfoService to new SAAS test class
- Fixed UUID string conversion issues in SaasSQLAppConversationInfoService
- Updated all user_id handling to properly convert string to UUID for database operations
- All tests pass: 4 new SAAS tests + 17 existing original tests
Co-authored-by: openhands <openhands@all-hands.dev>
- Add SaasAppConversationInfoServiceInjector to properly inject enterprise service
- Modify base config to use enterprise injector when OPENHANDS_CONFIG_CLS contains 'saas'
- Ensure OPENHANDS_CONFIG_CLS is set in saas_server.py for proper SAAS mode detection
- Clean up stored_conversation_metadata.py imports and exports
This ensures that when launching the enterprise server with uvicorn saas_server:app,
the overridden _secure_select() method with user-based filtering is used instead
of the base OSS implementation.
Co-authored-by: openhands <openhands@all-hands.dev>
- Create new ConversationMetadataSaas model with conversation_id, user_id, org_id
- Remove github_user_id, user_id, org_id from StoredConversationMetadata
- Update all enterprise clients to use ConversationMetadataSaas for user/org lookups
- Add database migration to create new table and migrate existing data
- Maintain backward compatibility in OpenHands core components
Co-authored-by: openhands <openhands@all-hands.dev>
- Added all 36 SQLAlchemy models that inherit from Base
- Added relevant enum classes (BillingSessionType, SubscriptionAccessStatus, etc.)
- Fixed missing comma in __all__ list
- Organized imports alphabetically for better maintainability
- Included StoredConversationMetadata alias from openhands core
This ensures all storage models are properly exposed through the storage module.
- Changed keycloak_user_id to id in User object instantiations
- Updated test assertions to use user.id instead of user.keycloak_user_id
- Fixed UUID generation for User.id fields
- Updated query filters to use User.id instead of User.keycloak_user_id
- Added missing uuid imports where needed
Files modified:
- enterprise/tests/unit/test_user_store.py: Fixed 3 test functions
- enterprise/tests/unit/test_org_store.py: Fixed 1 test function
- enterprise/tests/unit/test_org_member_store.py: Fixed 6 test functions
- enterprise/tests/unit/test_models.py: Fixed user creation and query
- enterprise/tests/unit/test_auth_routes.py: Fixed mock object attributes
These changes align the tests with the updated User model schema where
keycloak_user_id has been replaced with a UUID id field.
- Add migration_status column to user_settings table in migration script
- Update UserSettings model with migration_status boolean field (default False)
- Add migration check in UserStore to prevent double migration
- Mark migrated records as True instead of hard deletion
- Filter non-migrated records in SaasSettingsStore
This ensures safe migration from user_settings to org-based structure
without data loss and prevents duplicate migrations.
- Renamed database table from org_user to org_member in migration 077
- Renamed OrgUser class to OrgMember in storage model
- Renamed OrgUserStore class to OrgMemberStore
- Updated all import statements and references across the codebase
- Updated relationship references in related models (User, Org, Role)
- Updated foreign key constraint names (ou_* -> om_*)
- Updated method names (get_org_user -> get_org_member, get_org_users -> get_org_members)
- Updated test files to use new naming conventions
- Renamed files: org_user.py -> org_member.py, org_user_store.py -> org_member_store.py
Co-authored-by: openhands <openhands@all-hands.dev>
- Remove org_id column and ForeignKey constraint from GitlabWebhook model
- Remove org relationship from GitlabWebhook model
- Remove gitlab_webhooks relationship from Org model
- Remove gitlab_webhook table modifications from migration 077
- Clean up imports in gitlab_webhook.py (removed ForeignKey, UUID, relationship imports)
Co-authored-by: openhands <openhands@all-hands.dev>
- Remove org_id column and ForeignKey constraint from UserRepositoryMap model
- Remove org relationship from UserRepositoryMap model
- Remove user_repos relationship from Org model
- Remove user-repos table modifications from migration 077
- Clean up imports in user_repo_map.py (removed ForeignKey, UUID, relationship)
This decouples the user-repos table from the org system as requested.
- Add ForeignKey import to StoredConversationMetadata model
- Add ForeignKey('org.id') constraint to org_id column
- Uncomment org relationship with back_populates='conversation_metadata'
- Ensures bidirectional relationship works properly with migration 077
Fixes: sqlalchemy.exc.NoForeignKeysError: Could not determine join condition between parent/child tables on relationship Org.conversation_metadata
Co-authored-by: openhands <openhands@all-hands.dev>
- Make org_id column nullable to match migration
- Comment out org relationship for tests to avoid foreign key constraint errors
- Add note about org_id column in test file
This resolves SQLAlchemy foreign key constraint errors in unit tests
where the org table doesn't exist in the test environment.
- Update all import paths from 'openhands.enterprise.*' to 'enterprise.*'
to match OpenHands repo structure (deploy repo used openhands.enterprise)
- Add comprehensive documentation files (migration guides, structure docs)
- Add example usage files for organizational features
- Add complete test suite for organizational models and stores
- Update all server routes, auth components, integrations, and storage files
- Ensure all cross-references use correct enterprise.* import structure
This completes the migration of organizational database structure from
deploy repo PR #1413 with all import paths corrected for OpenHands repo.
- Add conversation_work.py for conversation work tracking
- Add feedback.py for user feedback storage
- Add github_app_installation.py for GitHub app installations
- Add maintenance_task.py for maintenance task processing
- Add stored_offline_token.py for offline token storage
- Update all imports to use enterprise.storage structure
These files are required by the test suite conftest.py for proper
database table creation during testing.
- Add organizational models: Org, User, Role, OrgUser with proper relationships
- Add corresponding store classes for database operations
- Add encryption utilities for sensitive data handling
- Add LiteLLM manager for organizational LLM configuration
- Add comprehensive migration file for organizational tables
- Update constants with ORG_SETTINGS_VERSION and version mapping
- Fix import paths to use enterprise structure
- Add org_id columns to existing tables for multi-tenancy support
Migrated from deploy repo PR #1413 'Org db litellm' (98 commits)
Resolves conflicts and updates paths for OpenHands repository structure
Co-authored-by: openhands <openhands@all-hands.dev>
- [ ] This change is worth documenting at https://docs.all-hands.dev/
- [ ] Include this change in the Release Notes. If checked, you **must** provide an **end-user friendly** description for your change below
## Summary of PR
**End-user friendly description of the problem this fixes or functionality this introduces.**
<!-- Summarize what the PR does, explaining any non-trivial design decisions. -->
## Change Type
---
**Summarize what the PR does, explaining any non-trivial design decisions.**
<!-- Choose the types that apply to your PR and remove the rest. -->
- [ ] Bug fix
- [ ] New feature
- [ ] Breaking change
- [ ] Refactor
- [ ] Other (dependency update, docs, typo fixes, etc.)
---
**Link of any specific issues this addresses:**
## Checklist
<!-- AI/LLM AGENTS: This checklist is for a human author to complete. Do NOT check either of the two boxes below. Leave them unchecked until a human has personally reviewed and tested the changes. -->
- [ ] I have read and reviewed the code and I understand what the code is doing.
- [ ] I have tested the code to the best of my ability and ensured it works as expected.
## Fixes
<!-- If this resolves an issue, link it here so it will close automatically upon merge. -->
Resolves #(issue)
## Release Notes
<!-- Check the box if this change is worth adding to the release notes. If checked, you must provide an
end-user friendly description for your change below the checkbox. -->
poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' 10 $N_PROCESSES '' 'haiku_run'
# get integration tests report
REPORT_FILE_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/*haiku*_maxiter_10_N* -name "report.md" -type f | head -n 1)
- name:Run integration test evaluation for DeepSeek
env:
SANDBOX_FORCE_REBUILD_RUNTIME:True
run:|
poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' 10 $N_PROCESSES '' 'deepseek_run'
# get integration tests report
REPORT_FILE_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek*_maxiter_10_N* -name "report.md" -type f | head -n 1)
- name:Run integration test evaluation for VisualBrowsingAgent (DeepSeek)
env:
SANDBOX_FORCE_REBUILD_RUNTIME:True
run:|
poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD VisualBrowsingAgent '' 15 $N_PROCESSES "t05_simple_browsing,t06_github_pr_browsing.py" 'visualbrowsing_deepseek_run'
# Find and export the visual browsing agent test results
REPORT_FILE_VISUALBROWSING_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/VisualBrowsingAgent/deepseek*_maxiter_15_N* -name "report.md" -type f | head -n 1)
cd evaluation/evaluation_outputs/outputs # Change to the outputs directory
tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/VisualBrowsingAgent/* # Only include the actual result directories
body: `[OpenHands](https://github.com/All-Hands-AI/OpenHands) started fixing the ${issueType}! You can monitor the progress [here](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).`
body: `[OpenHands](https://github.com/OpenHands/OpenHands) started fixing the ${issueType}! You can monitor the progress [here](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).`
});
- name:Install OpenHands
@@ -233,7 +233,7 @@ jobs:
if (isExperimentalLabel || isIssueCommentExperimental || isReviewCommentExperimental) {
stale-issue-message:'This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
stale-pr-message:'This PR is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
days-before-stale:30
exempt-issue-labels:'tracked'
close-issue-message:'This issue was closed because it has been stalled for over 30 days with no activity.'
close-pr-message:'This PR was closed because it has been stalled for over 30 days with no activity.'
days-before-close:7
operations-per-run:150
stale-issue-message:'This issue is stale because it has been open for 40 days with no activity. Remove the stale label or leave a comment, otherwise it will be closed in 10 days.'
stale-pr-message:'This PR is stale because it has been open for 40 days with no activity. Remove the stale label or leave a comment, otherwise it will be closed in 10 days.'
days-before-stale:40
exempt-issue-labels:roadmap,backlog,app-team
close-issue-message:'This issue was automatically closed due to 50 days of inactivity. We do this to help keep the issues somewhat manageable and focus on active issues.'
close-pr-message:'This PR was closed because it had no activity for 50 days. If you feel this was closed in error, and you would like to continue the PR, please resubmit or let us know.'
"This issue has been labeled as **good first issue**, which means it's a great place to get started with the OpenHands project.\n\n" +
"If you're interested in working on it, feel free to! No need to ask for permission.\n\n" +
"Be sure to check out our [development setup guide](" + repoUrl + "/blob/main/Development.md) to get your environment set up, and follow our [contribution guidelines](" + repoUrl + "/blob/main/CONTRIBUTING.md) when you're ready to submit a fix.\n\n" +
"Feel free to join our developer community on [Slack](https://all-hands.dev/joinslack). You can ask for [help](https://openhands-ai.slack.com/archives/C078L0FUGUX), [feedback](https://openhands-ai.slack.com/archives/C086ARSNMGA), and even ask for a [PR review](https://openhands-ai.slack.com/archives/C08D8FJ5771).\n\n" +
@@ -19,6 +19,7 @@ Before pushing any changes, you MUST ensure that any lint errors or simple test
* If you've made changes to the backend, you should run `pre-commit run --config ./dev_config/python/.pre-commit-config.yaml` (this will run on staged files).
* If you've made changes to the frontend, you should run `cd frontend && npm run lint:fix && npm run build ; cd ..`
* If you've made changes to the VSCode extension, you should run `cd openhands/integrations/vscode && npm run lint:fix && npm run compile ; cd ../../..`
The pre-commit hooks MUST pass successfully before pushing any changes to the repository. This is a mandatory requirement to maintain code quality and consistency.
@@ -29,6 +30,12 @@ then re-run the command to ensure it passes. Common issues include:
- Trailing whitespace
- Missing newlines at end of files
## Git Best Practices
- Prefer specific `git add <filename>` instead of `git add .` to avoid accidentally staging unintended files
- Be especially careful with `git reset --hard` after staging files, as it will remove accidentally staged files
- When remote has new changes, use `git fetch upstream && git rebase upstream/<branch>` on the same branch
## Repository Structure
Backend:
- Located in the `openhands` directory
@@ -60,6 +67,132 @@ Frontend:
- Mutation hooks should follow the pattern use[Action] (e.g., `useDeleteConversation`)
- Architecture rule: UI components → TanStack Query hooks → Data Access Layer (`frontend/src/api`) → API endpoints
VSCode Extension:
- Located in the `openhands/integrations/vscode` directory
- Setup: Run `npm install` in the extension directory
- Linting:
- Run linting with fixes: `npm run lint:fix`
- Check only: `npm run lint`
- Type checking: `npm run typecheck`
- Building:
- Compile TypeScript: `npm run compile`
- Package extension: `npm run package-vsix`
- Testing:
- Run tests: `npm run test`
- Development Best Practices:
- Use `vscode.window.createOutputChannel()` for debug logging instead of `showErrorMessage()` popups
- Pre-commit process runs both frontend and backend checks when committing extension changes
## Enterprise Directory
The `enterprise/` directory contains additional functionality that extends the open-source OpenHands codebase. This includes:
- Authentication and user management (Keycloak integration)
@@ -113,19 +113,19 @@ individual, or aggression toward or disparagement of classes of individuals.
**Consequence**: A permanent ban from any sort of public interaction within the
community.
### Slack and Discord Etiquettes
### Slack Etiquettes
These Slack and Discord etiquette guidelines are designed to foster an inclusive, respectful, and productive environment for all community members. By following these best practices, we ensure effective communication and collaboration while minimizing disruptions. Let’s work together to build a supportive and welcoming community!
These Slack etiquette guidelines are designed to foster an inclusive, respectful, and productive environment for all community members. By following these best practices, we ensure effective communication and collaboration while minimizing disruptions. Let’s work together to build a supportive and welcoming community!
- Communicate respectfully and professionally, avoiding sarcasm or harsh language, and remember that tone can be difficult to interpret in text.
- Use threads for specific discussions to keep channels organized and easier to follow.
- Tag others only when their input is critical or urgent, and use @here, @channel or @everyone sparingly to minimize disruptions.
- Be patient, as open-source contributors and maintainers often have other commitments and may need time to respond.
- Post questions or discussions in the most relevant channel (e.g., for [slack - #general](https://openhands-ai.slack.com/archives/C06P5NCGSFP) for general topics, [slack - #questions](https://openhands-ai.slack.com/archives/C06U8UTKSAD) for queries/questions, [discord - #general](https://discord.com/channels/1222935860639563850/1222935861386018885)).
- Post questions or discussions in the most relevant channel (e.g., for [slack - #general](https://openhands-ai.slack.com/archives/C06P5NCGSFP) for general topics, [slack - #questions](https://openhands-ai.slack.com/archives/C06U8UTKSAD) for queries/questions.
- When asking for help or raising issues, include necessary details like links, screenshots, or clear explanations to provide context.
- Keep discussions in public channels whenever possible to allow others to benefit from the conversation, unless the matter is sensitive or private.
- Always adhere to [our standards](https://github.com/All-Hands-AI/OpenHands/blob/main/CODE_OF_CONDUCT.md#our-standards) to ensure a welcoming and collaborative environment.
- If you choose to mute a channel, consider setting up alerts for topics that still interest you to stay engaged. For Slack, Go to Settings → Notifications → My Keywords to add specific keywords that will notify you when mentioned. For example, if you're here for discussions about LLMs, mute the channel if it’s too busy, but set notifications to alert you only when “LLMs” appears in messages. Also for Discord, go to the channel notifications and choose the option that best describes your need.
- Always adhere to [our standards](https://github.com/OpenHands/OpenHands/blob/main/CODE_OF_CONDUCT.md#our-standards) to ensure a welcoming and collaborative environment.
- If you choose to mute a channel, consider setting up alerts for topics that still interest you to stay engaged. For Slack, Go to Settings → Notifications → My Keywords to add specific keywords that will notify you when mentioned. For example, if you're here for discussions about LLMs, mute the channel if it’s too busy, but set notifications to alert you only when “LLMs” appears in messages.
The OpenHands community is built around the belief that (1) AI and AI agents are going to fundamentally change the way
we build software, and (2) if this is true, we should do everything we can to make sure that the benefits provided by
such powerful technology are accessible to everyone.
OpenHands is a community of engineers, academics, and enthusiasts reimagining software development for an AI-powered world.
If this resonates with you, we'd love to have you join us in our quest!
## Mission
## 🤝 How to Join
It’s very clear that AI is changing software development. We want the developer community to drive that change organically, through open source.
Check out our [How to Join the Community section.](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-how-to-join-the-community)
So we’re not just building friendly interfaces for AI-driven development. We’re publishing _building blocks_ that empower developers to create new experiences, tailored to your own habits, needs, and imagination.
## 💪 Becoming a Contributor
## Ethos
We welcome contributions from everyone! Whether you're a developer, a researcher, or simply enthusiastic about advancing
the field of software engineering with AI, there are many ways to get involved:
We have two core values: **high openness** and **high agency**. While we don’t expect everyone in the community to embody these values, we want to establish them as norms.
- **Code Contributions:** Help us develop new core functionality, improve our agents, improve the frontend and other
interfaces, or anything else that would help make OpenHands better.
- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in
evaluating the models, or suggest improvements.
- **Feedback and Testing:** Use the OpenHands toolset, report bugs, suggest features, or provide feedback on usability.
### High Openness
For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
We welcome anyone and everyone into our community by default. You don’t have to be a software developer to help us build. You don’t have to be pro-AI to help us learn.
## Code of Conduct
Our plans, our work, our successes, and our failures are all public record. We want the world to see not just the fruits of our work, but the whole process of growing it.
We have a [Code of Conduct](./CODE_OF_CONDUCT.md) that we expect all contributors to adhere to.
Long story short, we are aiming for an open, welcoming, diverse, inclusive, and healthy community.
All contributors are expected to contribute to building this sort of community.
We welcome thoughtful criticism, whether it’s a comment on a PR or feedback on the community as a whole.
## 🛠️ Becoming a Maintainer
### High Agency
For contributors who have made significant and sustained contributions to the project, there is a possibility of joining
the maintainer team. The process for this is as follows:
Everyone should feel empowered to contribute to OpenHands. Whether it’s by making a PR, hosting an event, sharing feedback, or just asking a question, don’t hold back!
1. Any contributor who has made sustained and high-quality contributions to the codebase can be nominated by any
maintainer. If you feel that you may qualify you can reach out to any of the maintainers that have reviewed your PRs and ask if you can be nominated.
2. Once a maintainer nominates a new maintainer, there will be a discussion period among the maintainers for at least 3 days.
3. If no concerns are raised the nomination will be accepted by acclamation, and if concerns are raised there will be a discussion and possible vote.
OpenHands gives everyone the building blocks to create state-of-the-art developer experiences. We experiment constantly and love building new things.
Note that just making many PRs does not immediately imply that you will become a maintainer. We will be looking
at sustained high-quality contributions over a period of time, as well as good teamwork and adherence to our [Code of Conduct](./CODE_OF_CONDUCT.md).
Coding, development practices, and communities are changing rapidly. We won’t hesitate to change direction and make big bets.
## Relationship to All Hands
OpenHands is supported by the for-profit organization [All Hands AI, Inc](https://www.all-hands.dev/).
All Hands was founded by three of the first major contributors to OpenHands:
- Xingyao Wang, a UIUC PhD candidate who got OpenHands to the top of the SWE-bench leaderboards
- Graham Neubig, a CMU Professor who rallied the academic community around OpenHands
- Robert Brennan, a software engineer who architected the user-facing features of OpenHands
All Hands is an important part of the OpenHands ecosystem. We’ve raised over $20M--mainly to hire developers and researchers who can work on OpenHands full-time, and to provide them with expensive infrastructure. ([Join us!](https://allhandsai.applytojob.com/apply/))
But we see OpenHands as much larger, and ultimately more important, than All Hands. When our financial responsibility to investors is at odds with our social responsibility to the community—as it inevitably will be, from time to time—we promise to navigate that conflict thoughtfully and transparently.
At some point, we may transfer custody of OpenHands to an open source foundation. But for now, the [Benevolent Dictator approach](http://www.catb.org/~esr/writings/cathedral-bazaar/homesteading/ar01s16.html) helps us move forward with speed and intention. If we ever forget the “benevolent” part, please: fork us.
@@ -13,15 +13,15 @@ To understand the codebase, please refer to the README in each module:
## Setting up Your Development Environment
We have a separate doc [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) that tells you how to set up a development workflow.
We have a separate doc [Development.md](https://github.com/OpenHands/OpenHands/blob/main/Development.md) that tells you how to set up a development workflow.
## How Can I Contribute?
There are many ways that you can contribute:
1.**Download and use** OpenHands, and send [issues](https://github.com/All-Hands-AI/OpenHands/issues) when you encounter something that isn't working or a feature that you'd like to see.
1.**Download and use** OpenHands, and send [issues](https://github.com/OpenHands/OpenHands/issues) when you encounter something that isn't working or a feature that you'd like to see.
2.**Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
3.**Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
3.**Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/OpenHands/OpenHands/labels/good%20first%20issue) that may be ones to start on.
## What Can I Build?
Here are a few ways you can help improve the codebase.
@@ -31,11 +31,11 @@ We're always looking to improve the look and feel of the application. If you've
for something that's bugging you, feel free to open up a PR that changes the [`./frontend`](./frontend) directory.
If you're looking to make a bigger change, add a new UI element, or significantly alter the style
of the application, please open an issue first, or better, join the #frontend channel in our Slack
of the application, please open an issue first, or better, join the #eng-ui-ux channel in our Slack
to gather consensus from our design team first.
#### Improving the agent
Our main agent is the CodeAct agent. You can [see its prompts here](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/agenthub/codeact_agent).
Our main agent is the CodeAct agent. You can [see its prompts here](https://github.com/OpenHands/OpenHands/tree/main/openhands/agenthub/codeact_agent).
Changes to these prompts, and to the underlying behavior in Python, can have a huge impact on user experience.
You can try modifying the prompts to see how they change the behavior of the agent as you use the app
@@ -54,11 +54,11 @@ The agent needs a place to run code and commands. When you run OpenHands on your
to do this by default. But there are other ways of creating a sandbox for the agent.
If you work for a company that provides a cloud-based runtime, you could help us add support for that runtime
by implementing the [interface specified here](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/base.py).
by implementing the [interface specified here](https://github.com/OpenHands/OpenHands/blob/main/openhands/runtime/base.py).
#### Testing
When you write code, it is also good to write tests. Please navigate to the [`./tests`](./tests) folder to see existing test suites.
At the moment, we have two kinds of tests: [`unit`](./tests/unit) and [`integration`](./evaluation/integration_tests). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
At the moment, we have these kinds of tests: [`unit`](./tests/unit), [`runtime`](./tests/runtime), and [`end-to-end (e2e)`](./tests/e2e). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
## Sending Pull Requests to OpenHands
@@ -84,7 +84,7 @@ For example, a PR title could be:
-`refactor: modify package path`
-`feat(frontend): xxxx`, where `(frontend)` means that this PR mainly focuses on the frontend component.
You may also check out previous PRs in the [PR list](https://github.com/All-Hands-AI/OpenHands/pulls).
You may also check out previous PRs in the [PR list](https://github.com/OpenHands/OpenHands/pulls).
### Pull Request description
- If your PR is small (such as a typo fix), you can go brief.
@@ -97,7 +97,7 @@ please include a short message that we can add to our changelog.
### Opening Issues
If you notice any bugs or have any feature requests please open them via the [issues page](https://github.com/All-Hands-AI/OpenHands/issues). We will triage based on how critical the bug is or how potentially useful the improvement is, discuss, and implement the ones that the community has interest/effort for.
If you notice any bugs or have any feature requests please open them via the [issues page](https://github.com/OpenHands/OpenHands/issues). We will triage based on how critical the bug is or how potentially useful the improvement is, discuss, and implement the ones that the community has interest/effort for.
Further, if you see an issue you like, please leave a "thumbs-up" or a comment, which will help us prioritize.
We would like to thank all the [contributors](https://github.com/All-Hands-AI/OpenHands/graphs/contributors) who have helped make OpenHands possible. We greatly appreciate your dedication and hard work.
We would like to thank all the [contributors](https://github.com/OpenHands/OpenHands/graphs/contributors) who have helped make OpenHands possible. We greatly appreciate your dedication and hard work.
## Open Source Projects
@@ -14,7 +14,7 @@ OpenHands includes and adapts the following open source projects. We are gratefu
- Description: AI pair programming tool. OpenHands has adapted and integrated its linter module for code-related tasks in [`agentskills utilities`](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/runtime/plugins/agent_skills/utils/aider)
- Description: AI pair programming tool. OpenHands has adapted and integrated its linter module for code-related tasks in [`agentskills utilities`](https://github.com/OpenHands/OpenHands/tree/main/openhands/runtime/plugins/agent_skills/utils/aider)
@@ -193,12 +195,12 @@ Here's a guide to the important documentation files in the repository:
- [/README.md](./README.md): Main project overview, features, and basic setup instructions
- [/Development.md](./Development.md) (this file): Comprehensive guide for developers working on OpenHands
- [/CONTRIBUTING.md](./CONTRIBUTING.md): Guidelines for contributing to the project, including code style and PR process
- [/docs/DOC_STYLE_GUIDE.md](./docs/DOC_STYLE_GUIDE.md): Standards for writing and maintaining project documentation
- [DOC_STYLE_GUIDE.md](https://github.com/All-Hands-AI/docs/blob/main/openhands/DOC_STYLE_GUIDE.md): Standards for writing and maintaining project documentation
- [/openhands/README.md](./openhands/README.md): Details about the backend Python implementation
- [/frontend/README.md](./frontend/README.md): Frontend React application setup and development guide
- [/containers/README.md](./containers/README.md): Information about Docker containers and deployment
- [/tests/unit/README.md](./tests/unit/README.md): Guide to writing and running unit tests
- [/evaluation/README.md](./evaluation/README.md): Documentation for the evaluation framework and benchmarks
- [/microagents/README.md](./microagents/README.md): Information about the microagents architecture and implementation
- [/skills/README.md](./skills/README.md): Information about the skills architecture and implementation
- [/openhands/server/README.md](./openhands/server/README.md): Server implementation details and API documentation
- [/openhands/runtime/README.md](./openhands/runtime/README.md): Documentation for the runtime environment and execution model
<a href="https://docs.all-hands.dev/usage/getting-started"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
<a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper%20on%20Arxiv-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Paper on Arxiv"></a>
<a href="https://docs.openhands.dev/sdk"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
Welcome to OpenHands (formerly OpenDevin), a platform for software development agents powered by AI.
<hr>
OpenHands agents can do anything a human developer can: modify code, run commands, browse the web,
call APIs, and yes—even copy code snippets from StackOverflow.
🙌Welcome to OpenHands, a [community](COMMUNITY.md) focused on AI-driven development. We’d love for you to [join us on Slack](https://dub.sh/openhands).
Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or [sign up for OpenHands Cloud](https://app.all-hands.dev) to get started.
There are a few ways to work with OpenHands:
> [!IMPORTANT]
> Using OpenHands for work? We'd love to chat! Fill out
> [this short form](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
> to join our Design Partner program, where you'll get early access to commercial features and the opportunity to provide input on our product roadmap.
### OpenHands Software Agent SDK
The SDK is a composable Python library that contains all of our agentic tech. It's the engine that powers everything else below.
Define agents in code, then run them locally, or scale to 1000s of agents in the cloud.
## ☁️ OpenHands Cloud
The easiest way to get started with OpenHands is on [OpenHands Cloud](https://app.all-hands.dev),
which comes with $20 in free credits for new users.
[Check out the docs](https://docs.openhands.dev/sdk) or [view the source](https://github.com/OpenHands/software-agent-sdk/)
## 💻 Running OpenHands Locally
### OpenHands CLI
The CLI is the easiest way to start using OpenHands. The experience will be familiar to anyone who has worked
with e.g. Claude Code or Codex. You can power it with Claude, GPT, or any other LLM.
OpenHands can also run on your local system using Docker.
See the [Running OpenHands](https://docs.all-hands.dev/usage/installation) guide for
system requirements and more information.
[Check out the docs](https://docs.openhands.dev/openhands/usage/run-openhands/cli-mode) or [view the source](https://github.com/OpenHands/OpenHands-CLI)
> [!WARNING]
> On a public network? See our [Hardened Docker Installation Guide](https://docs.all-hands.dev/usage/runtimes/docker#hardened-docker-installation)
> to secure your deployment by restricting network binding and implementing additional security measures.
### OpenHands Local GUI
Use the Local GUI for running agents on your laptop. It comes with a REST API and a single-page React application.
The experience will be familiar to anyone who has used Devin or Jules.
[Check out the docs](https://docs.openhands.dev/openhands/usage/run-openhands/local-setup) or view the source in this repo.
You can try it with a free $10 credit by [signing in with your GitHub account](https://app.all-hands.dev).
> **Note**: If you used OpenHands before version 0.44, you may want to run `mv ~/.openhands-state ~/.openhands` to migrate your conversation history to the new location.
OpenHands Cloud comes with source-available features and integrations:
- Integrations with Slack, Jira, and Linear
- Multi-user support
- RBAC and permissions
- Collaboration features (e.g., conversation sharing)
You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
### OpenHands Enterprise
Large enterprises can work with us to self-host OpenHands Cloud in their own VPC, via Kubernetes.
OpenHands Enterprise can also work with the CLI and SDK above.
When you open the application, you'll be asked to choose an LLM provider and add an API key.
[Anthropic's Claude Sonnet 4](https://www.anthropic.com/api) (`anthropic/claude-sonnet-4-20250514`)
works best, but you have [many options](https://docs.all-hands.dev/usage/llms).
OpenHands Enterprise is source-available--you can see all the source code here in the enterprise/ directory,
but you'll need to purchase a license if you want to run it for more than one month.
## 💡 Other ways to run OpenHands
Enterprise contracts also come with extended support and access to our research team.
> [!WARNING]
> OpenHands is meant to be run by a single user on their local workstation.
> It is not appropriate for multi-tenant deployments where multiple users share the same instance. There is no built-in authentication, isolation, or scalability.
>
> If you're interested in running OpenHands in a multi-tenant environment, check out the source-available, commercially-licensed
Learn more at [openhands.dev/enterprise](https://openhands.dev/enterprise)
You can [connect OpenHands to your local filesystem](https://docs.all-hands.dev/usage/runtimes/docker#connecting-to-your-filesystem),
run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/usage/how-to/headless-mode),
interact with it via a [friendly CLI](https://docs.all-hands.dev/usage/how-to/cli-mode),
or run it on tagged issues with [a github action](https://docs.all-hands.dev/usage/how-to/github-action).
### Everything Else
Visit [Running OpenHands](https://docs.all-hands.dev/usage/installation) for more information and setup instructions.
Check out our [Product Roadmap](https://github.com/orgs/openhands/projects/1), and feel free to
[open up an issue](https://github.com/OpenHands/OpenHands/issues) if there's something you'd like to see!
If you want to modify the OpenHands source code, check out [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
You might also be interested in our [evaluation infrastructure](https://github.com/OpenHands/benchmarks), our [chrome extension](https://github.com/OpenHands/openhands-chrome-extension/), or our [Theory-of-Mind module](https://github.com/OpenHands/ToM-SWE).
Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/usage/troubleshooting) can help.
All our work is available under the MIT license, except for the `enterprise/` directory in this repository (see the [enterprise license](enterprise/LICENSE) for details).
The core `openhands` and `agent-server` Docker images are fully MIT-licensed as well.
## 📖 Documentation
<a href="https://deepwiki.com/All-Hands-AI/OpenHands"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki" title="Autogenerated Documentation by DeepWiki"></a>
To learn more about the project, and for tips on using OpenHands,
check out our [documentation](https://docs.all-hands.dev/usage/getting-started).
There you'll find resources on how to use different LLM providers,
troubleshooting resources, and advanced configuration options.
## 🤝 How to Join the Community
OpenHands is a community-driven project, and we welcome contributions from everyone. We do most of our communication
through Slack, so this is the best place to start, but we also are happy to have you contact us on Discord or Github:
- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-3847of6xi-xuYJIPa6YIPg4ElbDWbtSA) - Here we talk about research, architecture, and future development.
- [Join our Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
- [Read or post Github Issues](https://github.com/All-Hands-AI/OpenHands/issues) - Check out the issues we're working on, or add your own ideas.
See more about the community in [COMMUNITY.md](./COMMUNITY.md) or find details on contributing in [CONTRIBUTING.md](./CONTRIBUTING.md).
## 📈 Progress
See the monthly OpenHands roadmap [here](https://github.com/orgs/All-Hands-AI/projects/1) (updated at the maintainer's meeting at the end of each month).
<img src="https://api.star-history.com/svg?repos=All-Hands-AI/OpenHands&type=Date" width="500" alt="Star History Chart">
</a>
</p>
## 📜 License
Distributed under the MIT License. See [`LICENSE`](./LICENSE) for more information.
## 🙏 Acknowledgements
OpenHands is built by a large number of contributors, and every contribution is greatly appreciated! We also build upon other open source projects, and we are deeply thankful for their work.
For a list of open source projects and licenses used in OpenHands, please see our [CREDITS.md](./CREDITS.md) file.
## 📚 Cite
```
@inproceedings{
wang2025openhands,
title={OpenHands: An Open Platform for {AI} Software Developers as Generalist Agents},
author={Xingyao Wang and Boxuan Li and Yufan Song and Frank F. Xu and Xiangru Tang and Mingchen Zhuge and Jiayi Pan and Yueqi Song and Bowen Li and Jaskirat Singh and Hoang H. Tran and Fuqiang Li and Ren Ma and Mingzhang Zheng and Bill Qian and Yanjun Shao and Niklas Muennighoff and Yizhe Zhang and Binyuan Hui and Junyang Lin and Robert Brennan and Hao Peng and Heng Ji and Graham Neubig},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=OJd3ayDDoF}
}
```
If you need help with anything, or just want to chat, [come find us on Slack](https://dub.sh/openhands).
title={{OpenHands: An Open Platform for AI Software Developers as Generalist Agents}},
author={Xingyao Wang and Boxuan Li and Yufan Song and Frank F. Xu and Xiangru Tang and Mingchen Zhuge and Jiayi Pan and Yueqi Song and Bowen Li and Jaskirat Singh and Hoang H. Tran and Fuqiang Li and Ren Ma and Mingzhang Zheng and Bill Qian and Yanjun Shao and Niklas Muennighoff and Yizhe Zhang and Binyuan Hui and Junyang Lin and Robert Brennan and Hao Peng and Heng Ji and Graham Neubig},
The **resolver is the odd one out** - it uses a 2-step process (clone to temp location, then copy to workspace) due to **legacy reasons** (it was originally developed as a separate app built on OH, not a component of OH). All other entry points use the standard pattern (clone directly into runtime workspace).
## Current State Analysis
### ✅ What Resolver Already Does Right:
- [x] Uses `create_runtime()` from setup.py for runtime creation
### ❌ What Needs to be Fixed:
- [ ]**Resolver uses legacy 2-step cloning instead of standard runtime.clone_or_init_repo()**
- [ ] Resolver has custom `initialize_runtime()` method that duplicates setup.py logic
- [ ] Resolver has custom `complete_runtime()` method with no setup.py equivalent
# Reasoning effort for o1 models (low, medium, high, or not set)
#reasoning_effort = "medium"
# Debugging enabled
#debug = false
@@ -49,6 +46,9 @@
# Maximum file size for uploads, in megabytes
#file_uploads_max_file_size_mb = 0
# Enable the browser environment
#enable_browser = true
# Maximum budget per task, 0.0 means no limit
#max_budget_per_task = 0.0
@@ -116,6 +116,9 @@ api_key = ""
# API version
#api_version = ""
# Reasoning effort for OpenAI o-series models (low, medium, high, or not set)
#reasoning_effort = "medium"
# Cost per input token
#input_cost_per_token = 0.0
@@ -186,7 +189,7 @@ model = "gpt-4o"
# Whether to use native tool calling if supported by the model. Can be true, false, or None by default, which chooses the model's default behavior based on the evaluation.
# ATTENTION: Based on evaluation, enabling native function calling may lead to worse results
# in some scenarios. Use with caution and consider testing with your specific use case.
@@ -6,7 +6,7 @@ that depends on the `base_image` **AND** a [Python source distribution](https://
The following command will generate a `Dockerfile` file for `nikolaik/python-nodejs:python3.12-nodejs22` (the default base image), an updated `config.sh` and the runtime source distribution files/folders into `containers/runtime`:
```bash
poetry run python3 openhands/runtime/utils/runtime_build.py\
poetry run python3 -m openhands.runtime.utils.runtime_build \
#- SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234} # enable this only if you want a specific non-root sandbox user but you will have to manually adjust permissions of ~/.openhands for this user
Use AI to tackle the toil in your backlog. Our agents have all the same tools as a human developer: they can modify code, run commands, browse the web, call APIs, and yes-even copy code snippets from StackOverflow.
description: "Real-world examples of what you can achieve with OpenHands"
---
Discover how developers and teams are using OpenHands to automate their software development workflows. From quick fixes to complex projects, see what's possible with AI-powered development assistance.
Check out the [#success-stories](https://www.linen.dev/s/openhands/c/success-stories) channel on our Slack for more!
## One of the cool things about OpenHands, and especially the Slack Integration, is the ability to empower folks who are on the ‘front lines’ with customers.
For example, often times Support and Customer Success teams will field bug reports, doc questions, and other ‘nits’ from customers. They tend to have few options to deal with this, other than file a feedback ticket with product teams and hope it gets prioritized in an upcoming sprint.
Instead, with tools like OpenHands and the Slack integration, they can request OpenHands to make fixes proactively and then have someone on the engineering team (like a lead engineer, a merge engineer, or even technical product manager) review the PR and approve it — thus reducing the cycle time for ‘quick wins’ from weeks to just a few hours.
<Update label="2025-06-08 OpenHands builds an interactive map for me" description="@Rodrigo Argenton Freire (ODLab)">
## Very simple example, but baby steps....
I am a professor of architecture and urban design. We built, me and some students, an interactive map prototype to help visitors and new students to find important places in the campus. Considering that we lack a lot of knowledge in programming, that was really nice to build and a smooth process.
We first created the main components with all-hands and then adjusted some details locally. Definitely, saved us a lot of time and money.
That's a prototype but we will have all the info by tuesday.
Big congratulations to the new [Tavily adapter](https://www.all-hands.dev/blog/building-a-provably-versatile-agent)... OpenHands and I have been beavering away at a Lightstreamer client library for most of this week but were getting a persistent (and unhelpful) "unexpected error" from the server.
Coming back to the problem today, after trying several unsuccessful fixes prompted by me, OH decided all by itself to search the web, and found the cause of the problem (of course it was simply CRLF line endings...). I was on the verge of giving up - good thing OH has more stamina than me!
This demonstrates how OpenHands' web search capabilities can help solve debugging issues that would otherwise require extensive manual research.
<Update label="2025-06-05 OpenHands updates my personal website for a new paper" description="@Xingyao Wang">
## I asked OpenHands to update my personal website for the "OpenHands Versa" paper.
It is an extremely trivial task: You just need to browse to arxiv, copy the author names, format them for BibTeX, and then modify the papers.bib file. But now I'm getting way too lazy to even open my IDE and actually do this one-file change!
I really don't like trying to fix issues with AWS, especially security groups and other finicky things like this. But I started up an instance and wasn't able to ssh in. So I asked OpenHands:
> Currently, the following ssh command is timing out:
## OpenHands builds Chrome extension for GitHub integration
I asked OpenHands to write a Chrome extension based on our [OpenHands Cloud API](https://docs.all-hands.dev/modules/usage/cloud/cloud-api). Once installed, you can now easily launch an OpenHands cloud session from your GitHub webpage/PR!
This demonstrates OpenHands' ability to create browser extensions and integrate with external APIs, enabling seamless workflows between GitHub and OpenHands Cloud.
## OpenHands tests UI automatically with visual browsing
Thanks to visual browsing -- OpenHands can actually test some simple UI by serving the website, clicking the button in the browser and looking at screenshots now!
Prompt is just:
```
I want to create a Hello World app in Javascript that:
* Displays Hello World in the middle.
* Has a button that when clicked, changes the greeting with a bouncing animation to fun versions of Hello.
* Has a counter for how many times the button has been clicked.
* Has another button that changes the app's background color.
```
Eager-to-work Sonnet 3.7 will test stuff for you without you asking!
This showcases OpenHands' visual browsing capabilities, enabling it to create, serve, and automatically test web applications through actual browser interactions and screenshot analysis.
Interesting story, I asked OpenHands to start an app on port 12000, it showed up on the app pane. I started using the app, and then it crashed... But because it crashed in OpenHands, OpenHands immediately saw the error message and started fixing the problem without me having to do anything. It was already fixing the problem before I even realized what was going wrong.
This demonstrates OpenHands' proactive monitoring capabilities - it doesn't just execute commands, but actively watches for errors and begins remediation automatically, often faster than human reaction time.
## Pair programming for interactive design projects
Used OpenHands as a pair programmer to do heavy lifting for a creative/interactive design project in p5js.
I usually take around 2 days for high fidelity interactions (planning strategy + writing code + circling back with designer), did this in around 5hrs instead with the designer watching curiously the entire time.
This showcases how OpenHands can accelerate creative and interactive design workflows, reducing development time by 75% while maintaining high quality output.
This agent implements the CodeAct idea ([paper](https://arxiv.org/abs/2402.01030), [tweet](https://twitter.com/xingyaow_/status/1754556835703751087)) that consolidates LLM agents’ **act**ions into a
unified **code** action space for both _simplicity_ and _performance_.
The conceptual idea is illustrated below. At each turn, the agent can:
1. **Converse**: Communicate with humans in natural language to ask for clarification, confirmation, etc.
2. **CodeAct**: Choose to perform the task by executing code
- Execute any valid Linux `bash` command
- Execute any valid `Python` code with [an interactive Python interpreter](https://ipython.org/). This is simulated through `bash` command, see plugin system below for more details.
<img src="https://github.com/All-Hands-AI/OpenHands/assets/16201837/97d747e3-29d8-4ccb-8d34-6ad1adb17f38" alt="OpenHands System Architecture Diagram Jul 4 2024" />
<p><em>OpenHands System Architecture Diagram (July 4, 2024)</em></p>
</div>
This is a high-level overview of the system architecture. The system is divided into two main components: the frontend and the backend. The frontend is responsible for handling user interactions and displaying the results. The backend is responsible for handling the business logic and executing the agents.
This Overview is simplified to show the main components and their interactions. For a more detailed view of the backend architecture, see the Backend Architecture section below.
# Backend Architecture
_**Disclaimer**: The backend architecture is a work in progress and is subject to change. The following diagram shows the current architecture of the backend based on the commit that is shown in the footer of the diagram._
2. Open the generated file in a PlantUML editor, e.g. Visual Studio Code with the PlantUML extension or [PlantText](https://www.planttext.com/)
3. Review the generated PUML and make all necessary adjustments to the diagram (add missing parts, fix mistakes, improve positioning).
_py2puml creates the diagram based on the type hints in the code, so missing or incorrect type hints may result in an incomplete or incorrect diagram._
4. Review the diff between the new and the previous diagram and manually check if the changes are correct.
_Make sure not to remove parts that were manually added to the diagram in the past and are still relevant._
5. Add the commit hash of the commit that was used to generate the diagram to the diagram footer.
6. Export the diagram as PNG and SVG files and replace the existing diagrams in the `docs/architecture` directory. This can be done with (e.g. [PlantText](https://www.planttext.com/))
The OpenHands Docker Runtime is the core component that enables secure and flexible execution of AI agent's action.
It creates a sandboxed environment using Docker, where arbitrary code can be run safely without risking the host system.
## Why do we need a sandboxed runtime?
OpenHands needs to execute arbitrary code in a secure, isolated environment for several reasons:
1. Security: Executing untrusted code can pose significant risks to the host system. A sandboxed environment prevents malicious code from accessing or modifying the host system's resources
2. Consistency: A sandboxed environment ensures that code execution is consistent across different machines and setups, eliminating "it works on my machine" issues
3. Resource Control: Sandboxing allows for better control over resource allocation and usage, preventing runaway processes from affecting the host system
4. Isolation: Different projects or users can work in isolated environments without interfering with each other or the host system
5. Reproducibility: Sandboxed environments make it easier to reproduce bugs and issues, as the execution environment is consistent and controllable
## How does the Runtime work?
The OpenHands Runtime system uses a client-server architecture implemented with Docker containers. Here's an overview of how it works:
1. User Input: The user provides a custom base Docker image
2. Image Building: OpenHands builds a new Docker image (the "OH runtime image") based on the user-provided image. This new image includes OpenHands-specific code, primarily the "runtime client"
3. Container Launch: When OpenHands starts, it launches a Docker container using the OH runtime image
4. Action Execution Server Initialization: The action execution server initializes an `ActionExecutor` inside the container, setting up necessary components like a bash shell and loading any specified plugins
5. Communication: The OpenHands backend (`openhands/runtime/impl/eventstream/eventstream_runtime.py`) communicates with the action execution server over RESTful API, sending actions and receiving observations
6. Action Execution: The runtime client receives actions from the backend, executes them in the sandboxed environment, and sends back observations
7. Observation Return: The action execution server sends execution results back to the OpenHands backend as observations
The role of the client:
- It acts as an intermediary between the OpenHands backend and the sandboxed environment
- It executes various types of actions (shell commands, file operations, Python code, etc.) safely within the container
- It manages the state of the sandboxed environment, including the current working directory and loaded plugins
- It formats and returns observations to the backend, ensuring a consistent interface for processing results
## How OpenHands builds and maintains OH Runtime images
OpenHands' approach to building and managing runtime images ensures efficiency, consistency, and flexibility in creating and maintaining Docker images for both production and development environments.
Check out the [relevant code](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/utils/runtime_build.py) if you are interested in more details.
### Image Tagging System
OpenHands uses a three-tag system for its runtime images to balance reproducibility with flexibility.
This is the first 16 digits of the MD5 of the directory hash for the source directory. This gives a hash
for only the openhands source
#### Lock Tag
This hash is built from the first 16 digits of the MD5 of:
- The name of the base image upon which the image was built (e.g.: `nikolaik/python-nodejs:python3.12-nodejs22`)
- The content of the `pyproject.toml` included in the image.
- The content of the `poetry.lock` included in the image.
This effectively gives a hash for the dependencies of Openhands independent of the source code.
#### Versioned Tag - Most Generic
This tag is a concatenation of openhands version and the base image name (transformed to fit in tag standard).
#### Build Process
When generating an image...
- **No re-build**: OpenHands first checks whether an image with the same **most specific source tag** exists. If there is such an image,
no build is performed - the existing image is used.
- **Fastest re-build**: OpenHands next checks whether an image with the **generic lock tag** exists. If there is such an image,
OpenHands builds a new image based upon it, bypassing all installation steps (like `poetry install` and
`apt-get`) except a final operation to copy the current source code. The new image is tagged with a
**source** tag only.
- **Ok-ish re-build**: If neither a **source** nor **lock** tag exists, an image will be built based upon the **versioned** tag image.
In versioned tag image, most dependencies should already been installed hence saving time.
- **Slowest re-build**: If all of the three tags don't exists, a brand new image is built based upon the base
image (Which is a slower operation). This new image is tagged with all the **source**, **lock**, and **versioned** tags.
This tagging approach allows OpenHands to efficiently manage both development and production environments.
1. Identical source code and Dockerfile always produce the same image (via hash-based tags)
2. The system can quickly rebuild images when minor changes occur (by leveraging recent compatible images)
3. The **lock** tag (e.g., `runtime:oh_v0.9.3_1234567890abcdef`) always points to the latest build for a particular base image, dependency, and OpenHands version combination
## Runtime Plugin System
The OpenHands Runtime supports a plugin system that allows for extending functionality and customizing the runtime environment. Plugins are initialized when the runtime client starts up.
Check [an example of Jupyter plugin here](https://github.com/All-Hands-AI/OpenHands/blob/ecf4aed28b0cf7c18d4d8ff554883ba182fc6bdd/openhands/runtime/plugins/jupyter/__init__.py#L21-L55) if you want to implement your own plugin.
*More details about the Plugin system are still under construction - contributions are welcomed!*
Key aspects of the plugin system:
1. Plugin Definition: Plugins are defined as Python classes that inherit from a base `Plugin` class
2. Plugin Registration: Available plugins are registered in an `ALL_PLUGINS` dictionary
3. Plugin Specification: Plugins are associated with `Agent.sandbox_plugins: list[PluginRequirement]`. Users can specify which plugins to load when initializing the runtime
4. Initialization: Plugins are initialized asynchronously when the runtime client starts
5. Usage: The runtime client can use initialized plugins to extend its capabilities (e.g., the JupyterPlugin for running IPython cells)
description: This guide walks you through the process of installing OpenHands Cloud for your GitHub repositories. Once
set up, it will allow OpenHands to work with your GitHub repository through the Cloud UI or straight from GitHub!
---
## Prerequisites
- Signed in to [OpenHands Cloud](https://app.all-hands.dev) with [a GitHub account](/usage/cloud/openhands-cloud).
## Adding GitHub Repository Access
You can grant OpenHands access to specific GitHub repositories:
1. Click on `Add GitHub repos` on the landing page.
2. Select your organization and choose the specific repositories to grant OpenHands access to.
<Accordion title="OpenHands permissions">
- OpenHands requests short-lived tokens (8-hour expiration) with these permissions:
- Actions: Read and write
- Commit statuses: Read and write
- Contents: Read and write
- Issues: Read and write
- Metadata: Read-only
- Pull requests: Read and write
- Webhooks: Read and write
- Workflows: Read and write
- Repository access for a user is granted based on:
- Permission granted for the repository
- User's GitHub permissions (owner/collaborator)
</Accordion>
3. Click `Install & Authorize`.
## Modifying Repository Access
You can modify GitHub repository access at any time by:
- Selecting `Add GitHub repos` on the landing page or
- Visiting the Settings page and selecting `Configure GitHub Repositories` under the `Integrations` tab
## Working With GitHub Repos in Openhands Cloud
Once you've granted GitHub repository access, you can start working with your GitHub repository. Use the `select a repo`
and `select a branch` dropdowns to select the appropriate repository and branch you'd like OpenHands to work on. Then
click on `Launch` to start the conversation!

## Working on Github Issues and Pull Requests Using Openhands
Giving GitHub repository access to OpenHands also allows you to work on GitHub issues and pull requests directly.
### Working with Issues
On your repository, label an issue with `openhands` or add a message starting with
`@openhands`. OpenHands will:
1. Comment on the issue to let you know it is working on it.
- You can click on the link to track the progress on OpenHands Cloud.
2. Open a pull request if it determines that the issue has been successfully resolved.
3. Comment on the issue with a summary of the performed tasks and a link to the PR.
### Working with Pull Requests
To get OpenHands to work on pull requests, mention `@openhands` in the comments to:
- Ask questions
- Request updates
- Get code explanations
## Next Steps
- [Learn about the Cloud UI](/usage/cloud/cloud-ui).
- [Use the Cloud API](/usage/cloud/cloud-api) to programmatically interact with OpenHands.
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.