Explore
MCP servers and skills: search, filter by where they run, and compare.
SWE-benchmarks-gen-harnessKentoShimizu
HostedGeneration harness for SWE-bench Verified experiments
SkillLink only★ 2Few stars
MCP servers and skills: search, filter by where they run, and compare.
Generation harness for SWE-bench Verified experiments
SkillLink only★ 2Few stars
SWE-bench repository patch localizer and regression verifier (Devin SWE style)
SkillLink only★ 8
Autonomous multi-agent AI coding assistant coordinating 21 specialized sub-agents with SWE-bench RAG
SkillLink only★ 1Few stars
Microsoft Build AI 2026 National 1st Place. Local codebase memory for AI coding agents: 63.8% Coverage@5, 75.2% Coverage@10, 60-65x lower context.
MCPLink only★ 16
Automated benchmark patch verification harness & fail-to-pass matrix (SWE-bench)
SkillLink only★ 8
AST code fault localization & regression test patch synthesizer (SWE-Bench)
SkillLink only★ 8
Autonomous coding agent with a sandboxed execution loop. Benchmarked on SWE-bench and MBPP.
MCPLink only★ 1Few stars
High-performance AI-native shell, process executor, snapshot engine, and MCP server in Rust.
MCPLink onlyFew stars
🔮 The Oracle — a deterministic reality predictor that judges any AI-generated Python code change Pass/Fail against a real test oracle. An open climb toward domain super-intelligence for software engi
MCPLink onlyFew stars
Who stands behind it
