Explore
MCP servers and skills: search, filter by where they run, and compare.
1–24 of 130 tools for “swe-bench”
Clear allswe-bench-pro-actiongreynewell
LocalGitHub Action for SWE-bench Pro evaluation powered by mcpbr
SkillMIT★ 1Few starsNo key
MCP servers and skills: search, filter by where they run, and compare.
1–24 of 130 tools for “swe-bench”
Clear allGitHub Action for SWE-bench Pro evaluation powered by mcpbr
SkillMIT★ 1Few starsNo key
Generation harness for SWE-bench Verified experiments
SkillLink only★ 2Few stars
SWE-bench evaluation framework demonstrating multi-model consultation improves accuracy
SkillMIT★ 1Few starsNo key
SWE-bench repository patch localizer and regression verifier (Devin SWE style)
SkillLink only★ 8
LLM code-agent framework — Thought→Code→Observation loop, process-isolated sandbox, MBPP + SWE-bench tracks, MCP tools, multi-model OpenRouter benchmarks. 42 School project.
PythonMIT★ 2Few starsNo key
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
Node.jsMIT★ 11kNo key
Is this SWE-bench-style task fair to grade an agent on? Agentic screening with verified evidence, measured against human annotations. Also an agent skill: /fairtask
SkillMITFew starsNo key
Reproducible recon/craft/audit agent pipeline for SWE-bench Verified. Official-graded, codex-attested, GPL-3.0. Run it yourself.
SkillGPL-3.0★ 8No key
Local-first MCP server that tells coding agents which files to read, and how sure it is. 97% Hit@10 on Java (SWE-bench Multilingual), 89% on Python (SWE-bench Lite), zero LLM cost. mcp-brain calibrate
PythonMIT★ 5No key
PythonMIT★ 2Few starsNo key
Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.
PythonMIT★ 154No key
SkillMIT★ 1Few starsNo key
基于 claude-code-from-scratch 二次开发的 coding agent（TS）：加入自我纠错闭环、本地 embedding 记忆、MCP、SWE-bench 评测 | A coding agent (TS) built on claude-code-from-scratch, adding self-correction, local embedding memory, MC
Node.jsMIT★ 1Few starsNo key
Fast, cheap judgment for AI coding agents: semantic search, focused reads and list picking in ~2s. CLI + MCP server on TypeSafe Jev. Benchmarked on SWE-bench.
PythonMIT★ 7No key
Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.
PythonApache-2.0★ 154No key
A blazing-fast, memory-safe neural network library for Rust that brings the power of FANN to the modern world.
Node.jsMIT★ 387No key
Benchmark ClaudeCode/Codex token usage across compression scenarios
SkillApache-2.0★ 8No key
Personal SWE-bench harvested from your own dev sessions — replay real fixes across agent harnesses and models, score against your own verified patch
SkillMIT★ 1Few starsNo key
Zero-LLM structural code retrieval for AI coding agents — tree-sitter index, BM25+dense+structural fusion, served over MCP.
PythonMIT★ 7No key
Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP · multi-model · Windows/CJK · listed in awesome-opensource-
PythonMIT★ 54No key
Scalable and extensible reinforcement learning for LM agents.
SkillApache-2.0★ 122No key
Architectural Moat: JIT-JEV Context OS — Epistemic runtime & JEV System 1 context gate for AI agents (L0 SQLite WAL <3ms, Epistemic Invariants I1–I10, CERN Zenodo DOI: 10.5281/zenodo.22649542)
PythonMIT★ 8No key
Who stands behind it
