Coding agents
Open SWE
Asynchronous coding-agent service focused on task intake, isolated execution and pull-request delivery.
Overview
Research summary
Open SWE is designed as an asynchronous software-engineering agent that can receive work from issue or collaboration systems, execute in isolated environments, validate changes and return reviewable pull requests. It builds on LangGraph/Deep Agents concepts while packaging the orchestration required for a deployable internal coding service. The project is a useful reference for the layer above an agent loop: task intake, environment provisioning, durable execution, validation and delivery.
This makes Open SWE complementary to interactive terminal agents. The interesting runtime boundary is not only model-to-tool execution but also the durable service around it: accepting jobs, provisioning isolated workspaces, tracking progress, validating results and publishing a pull request that another engineer can review. Those concerns map closely to production agent infrastructure and provide a reference for keeping orchestration deterministic while allowing the coding agent itself to remain replaceable or independently evolvable.
Repository summary
- Stars
- 10,711
- Open issues
- 22
- Last push
- 2026-09-14
- Commits, 90 days
- 870
- Repository activity
- Very active · 99/100
- Version
- desktop-v0.2.9
Recorded catalogue figures. View repository data and provenance →
Classification
Pricing & services
Paid services unknown
Whether the provider offers paid products or services has not been established.
Licence scope
Implementation
Recorded implementation details and interfaces for Open SWE.
Implementation details
Python agent with supporting web application
- Languages
- Python
- Repository type
- source
Recorded interfaces and capabilities
Licence scope
Repository
Repository snapshots, release information and recorded maintenance signals.
Repository snapshot
- Stars
- 10,711
- Open issues
- 22
- Last push
- 2026-09-14
- Commits, 90 days
- 870
- Repository activity
- Very active · 99/100
- Archived
- No
Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).
Release information
- Current version
- desktop-v0.2.9
- Version source
- github-release
- Version scope
- langchain-ai/open-swe
- Version recorded
- 2026-09-14
- Latest release tag
- desktop-v0.2.9
- Release published
- 2026-09-11
- Default branch
- main
- Head commit
e2c8d7814ef22a982d585b4df3574e50e1e93611
Maintenance and provenance
- Catalogue snapshot
- 2026-10-06
- Repository metrics recorded
- 2026-09-14
- Stars source
- GitHub snapshot
- Last push source
- GitHub snapshot
- Repository metrics stale
- No
- Snapshot repository
- langchain-ai/open-swe
Documentation
Recorded references and research provenance for this entry.
Recorded sources 6
- https://github.com/langchain-ai/open-swe Project page · Linked repository · Research reference · Repository metric snapshot
- https://raw.githubusercontent.com/langchain-ai/open-swe/HEAD/README.md Research reference
- https://www.langchain.com/blog/open-swe-an-open-source-framework-for-internal-coding-agents Research reference
- https://www.youtube.com/watch?v=TaYVvXbOs8c Research reference
- https://www.youtube.com/oembed?url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DTaYVvXbOs8c&format=json Research reference
- https://www.youtube.com/@LangChain Research reference
Research metadata
- Research date
- 2026-09-14
- Catalogue snapshot
- 2026-10-06
- Repository metrics recorded
- 2026-09-14
Community & social 3 channels
Video
- YouTubeLangChain (shared channel)OfficialDemos
Link details for YouTube — LangChain (shared channel)
- Access
- Public
- Last checked
Social & updates
- XLangChain (shared channel)Official
Link details for X — LangChain (shared channel)
- Last checked
- LinkedInLangChain (shared channel)Official
Link details for LinkedIn — LangChain (shared channel)
- Last checked