Explore

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

Node.js·MIT·★ 11k·No 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

Skill·MIT·Few stars·No 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

Python·MIT·★ 5·No 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.

Python·MIT·★ 154·No 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.js·MIT·★ 1·Few stars·No 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.

Python·MIT·★ 7·No 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.

Python·Apache-2.0·★ 154·No key

Zero-LLM structural code retrieval for AI coding agents — tree-sitter index, BM25+dense+structural fusion, served over MCP.

Python·MIT·★ 7·No key

Best-of-N for coding agents with a same-model verifier, run your task N times in isolated git worktrees and apply the verified winner. A /ultra command for opencode, plus a standalone CLI.

Skill·MIT·★ 4·Few stars·No key

Node.js·MIT·★ 2·Few stars·No key

Agentic-first Cursor Rules powered by MiniMax M3 - clarify-first prompting, interleaved thinking, and full tool orchestration for production-ready AI coding

Skill·MIT·★ 126·No key

Placebo-controlled benchmark of the most-starred coding agent skills

Skill·MIT·★ 19·No key

开源 Windows 本地 AI 工作台｜OpenAI-compatible + Claude CLI，99 个桌面/Office 工具，可回退文件操作与可视化多 Agent 工作流。

Skill·Apache-2.0·★ 40·No key

Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed markdown files in your repo; agents consult them before writi

Python·MIT·★ 27·No key

Context engine for coding agents. Indexes a repo into a multi-layer knowledge graph and serves precise architectural context over MCP. 78.2% on SWE-bench Verified at $0.22/instance. MIT.

Python·MIT·★ 2·Few stars·No key

5-agent LangGraph system that autonomously resolves GitHub issues, benchmarked across single-agent baseline, paid API, and open-weight HPC configurations on SWE-bench Lite

Skill·MIT·★ 1·Few stars·No key

Fully local MCP retrieval tool for coding agents. 161M encoder, ~1s per tool call, no API, no LLM in the query path. No file reads: line numbers, callers, callees and exact call sites, packed to a tok

Go·MIT·★ 5·No key

Your coding agent is smart. Your legacy codebase is the problem. Reify gives it the context to understand and safely change large, unfamiliar codebases — 100% locally.

Skill·Apache-2.0·★ 3·Few stars·No key

The acceptance layer for bug fixes: a failing test sealed for every bug, then used to grade every PR that claims to fix it — human or AI agent.

Python·MIT·★ 5·No key

Transparent feedback compression middleware for LLM coding agents

Python·MIT·★ 1·Few stars·No key

Find the agent-memory benchmark that fits your system in one offline command.

Skill·MIT·Few stars·No key

Robot Framework library for testing MCP servers, Agent Skills, Hooks, SubAgents, and coding-agent CLIs — provider-agnostic via LiteLLM, BFCL-grade tool-call matching, statistical N≥10 by default.

Python·Apache-2.0·★ 1·Few stars·No key