Overview & Capability
Autonomous software engineering agent created by Princeton University. Features an Agent-Computer Interface (ACI) specifically optimized for LLM repository exploration, editing, and test execution.
Key Highlights
- Specialized Agent-Computer Interface (ACI) for code file navigation
- Top-tier performance on the competitive SWE-bench benchmark
- Supports Claude 3.5 Sonnet, GPT-4o, and local models
Robbie's Independent Take
Verified: 2026-10-11
Excellent candidate for local execution with zero cloud lock-in. For 7B-8B parameter models, budget at least 8 GB of unified memory or VRAM (Q4_K_M quantization). For 32B-70B models, aim for 24 GB+ to maintain interactive throughput without CPU offload penalties.
Alternatives & Replaces
- Manual bug triage and patch drafting