SWE-agent
The Princeton research agent that introduced the Agent-Computer Interface (ACI) concept: carefully designed commands, file viewers, and feedback formats that dramatically improve LLM performance on real GitHub issues (SWE-bench).
View source on GitHubKey takeaways
- 01
ACI design (commands + viewers + feedback) is a measurable performance lever
- 02
Constrained, purpose-built tools beat raw shell access
- 03
Benchmark-driven iteration (SWE-bench) keeps harness claims honest
Flows built on this research
Agent Architecture
Design the Agent-Computer Interface (ACI)
Apply SWE-agent's key finding: agents perform dramatically better when their commands, viewers, and feedback are designed for models, not humans.
5 steps · 90-120 minutes
Harness Engineering
Sandbox Untrusted Code Execution
Contain what your agent runs: isolated execution environments with resource limits, network policy, and workspace mounting done right.
4 steps · 120-180 minutes