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
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, determi
SkillMIT★ 27kNo 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
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that r
SkillMIT★ 1.0kNo 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
Generate and validate ISO 20022 payment files (pain.001 v03-v12, pain.008) from CSV, SQLite, JSON, or Parquet. XSD and SEPA scheme validation, pain.002 and camt.053 parsers and builders, plus a CLI, R
PythonApache-2.0★ 49No key
MCP server for Windows desktop automation. Incremental perception instead of a screenshot per step: measured 16.9x fewer tokens per action than the alternatives, with the benchmarks to check it.
PythonMIT★ 4Few starsNo key
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
PythonApache-2.0★ 66No 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
Governance-grade, OKF-compatible knowledge-base format with a single-writer MCP server and CLI. Pre-release.
PythonApache-2.0★ 30No key
Fast PDF tools for AI agents: 31 tools in one Rust binary. CLI, MCP server and library.
Node.jsMIT★ 1Few starsNo key
Create Word, Excel, and PowerPoint files (.docx, .xlsx, .pptx) from plain JSON or fully typed APIs — generate, parse, and patch. Built for AI agents, LLM tool-calling, and hand-written code alike; no
SkillMIT★ 38No key
Recordings in. Agent-ready evidence out. Local-first MCP for transcripts, keyframes, OCR, speakers, and wall-clock evidence.
PythonMIT★ 31No key
The Obsidian MCP server that needs no plugin, no running Obsidian app — and doesn't blow your context window. Filesystem-direct: single-digit-ms keyword search, ~26 ms local semantic search, ~2 KB pay
SkillMIT★ 31No key
Context infrastructure for AI-assisted development — on-demand Obsidian vault access via MCP
PythonMIT★ 11No key
Raw documents (Markdown, HTML, plain text) → structured bridge format <D>?<H><B> — with adaptive compression that keeps you under token budget.
SkillApache-2.0★ 6No key
Generate & validate ISO 20022 pain.001 payment files from Claude Desktop, Cursor & other MCP clients — pain.001 v03-v12, pain.008, SEPA SCT/SDD/INST, cross-border rulebook checks. Part of the ISO 2002
PythonApache-2.0★ 1Few starsNo key
Temporal knowledge engine for markdown vaults — graph + bitemporal facts + agent memory over MCP. Local, model-free, benchmarked: 95.9% R@5 on LongMemEval (all 500).
Node.jsMITFew starsNo key
Unified MCP access to genomic archives, reference databases and indexed sequencing files
DockerMIT★ 3Few starsNo key
Extract complete, reviewable figures and tables from PDF, arXiv, and HTML papers — an installable AI-agent skill and CLI with contact-sheet QA.
SkillMIT★ 5No key
Temporal reasoning for AI agents — deadlines, schedules, sequences, duration estimation (PERT), and decay models. One .atime file. Rust core + MCP server.
SkillMIT★ 4Few starsNo key
Cursor-style semantic code search as an MCP plugin for Claude Code. Instead of grepping 50 files and sending 30,000 tokens to Claude, VecGrep returns the top 8 semantically relevant code chunks (~1,60
PythonMIT★ 9No key
AI quoting agent for electronics distributors. Parses RFQ documents (PDF, Excel, Word) with Claude, looks up every line item against your SAP, Epicor, Oracle, or Dynamics 365 ERP via MCP connectors, a
PythonMITFew starsNo key
MCP server with a context ledger: cryptographically signed receipts of exactly which file versions the model was shown. Honest benchmarks: no real-world token savings (-1.4% measured); ~72% applies on
Node.jsMIT★ 4Few starsNo key
Who stands behind it
