MCP servers and skills: search, filter by where they run, and compare.
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
PythonMIT★ 6.2kNo key
Memory library for building stateful agents
Hosted by authorAGPL-3.0★ 7.7kNo key
Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/Long
PythonApache-2.0★ 10No key
LynxMCP: local MCP server for the code questions grep can't answer. Call graph and blast radius, hybrid semantic + lexical code search on ONNX Runtime, library docs and PDFs as sources. No cloud, no P
PythonApache-2.0★ 10No key
Local-first search across your workspace, built for humans and AI agents.
Node.jsApache-2.0★ 4.1kNo key
Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fift
SkillMIT★ 9.4kNo key
The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.
PythonAGPL-3.0★ 381No key
Zig code intelligence server and MCP toolset for AI agents. Fast tree, outline, symbol, search, read, edit, deps, snapshot, and remote GitHub repo queries.
SkillBSD-3-Clause★ 1.4kNo key
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
SkillApache-2.0★ 686No key
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no chan
GoMIT★ 905No key
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Node.jsApache-2.0★ 331No key
ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a conceptual fork of OrientDB, the first Multi-Model DBMS. ArcadeDB supports Vecto
SkillApache-2.0★ 1.2kNo key
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
SkillMIT★ 950No key
Remote jobs MCP server — search 100,000+ remote jobs, post listings, find candidates, and check salary benchmarks from Claude, ChatGPT, Cursor, and any MCP client. Free, no API key required.
Hosted by authorMIT★ 21No key
Coding agent memory for Claude Code, Codex, Cursor and 38 more, built from the session history already on your disk. Local search, MCP and hooks, no LLM, one Go binary.
GoMIT★ 1.2kNo key
Text-to-SQL access control: schema selection that gives the LLM only the tables the caller is allowed to read. Row-level-security-aware table pruning for LangChain, MCP and any SQL agent. Postgres, Or
PythonApache-2.0★ 103No key
Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5
PythonMIT★ 73No key
Graph-native code intelligence that replaces embedding-based RAG with deterministic program understanding.
SkillMIT★ 160No key
Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code changes. Self-host for free.
Hosted by authorMIT★ 114No key
Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.
Node.jsApache-2.0★ 111No key
Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ran
SkillMIT★ 120No key
MCP server for measured local-LLM benchmarks from the AGmind claim registry — AMD Strix Halo (Ryzen AI Max+ 395) llama.cpp numbers today, NVIDIA DGX Spark on the bench. search_claims, get_claim, list_
Node.jsApache-2.0★ 4Few starsNo key
Open-source AI coding agent and agent runtime: one binary, any model, MCP-native. Runs in terminal, CI, or as a daemon.
SkillApache-2.0★ 162No key
Who stands behind it
