SWE-agent · SWE-agent team (Princeton/Stanford)
The NeurIPS-2024 research harness from the SWE-bench team that pioneered the agent-computer-interface concept: takes a GitHub issue and autonomously fixes it in a containerized environment with any LM, and remains the reference batch-evaluation harness for academic agent research.
Identity
| Homepage | https://swe-agent.com |
|---|---|
| Repository | https://github.com/SWE-agent/SWE-agent |
| License | open-source |
| Domain | coding |
| Form factor | cli |
Model support
| Model-agnostic | ✓ yes |
|---|---|
| Native models | — |
| Local models | ✓ yes |
| Pricing | byok |
Extensibility
| MCP client | ? unknown |
|---|---|
| Agent Skills support | ○ no |
| Plugins / hooks | ✓ yes |
Execution & safety
| Sandboxing | container |
|---|---|
| Autonomy spectrum | autonomous-local |
| Subagents | ○ no |
| Parallel sessions | ✓ yes |
| Context management | compaction |
Integration & evidence
| Headless / API | ✓ yes |
|---|---|
| GitHub integration | ✓ yes |
| Sources |
✓ profile last verified 2026-07-08 · benchmark figures are vendor-reported unless a source states otherwise