MCP servers and skills: search, filter by where they run, and compare.
GLiNER2 MCP gives your agent three practical superpowers: extract entities, classify meaning, and produce structured JSON from plain language
PythonMIT★ 4Few starsNo key
Deterministic-first PII/PHI de-identification you can prove: benchmarked recall, jurisdiction policy packs, reversible tokenization, audit trail. CLI + library + GitHub Action; optional GLiNER / Gemma
PythonApache-2.0★ 9No key
Embedded, local-first agent memory. No server, no daemon, no mandatory cloud key.
PythonApache-2.0★ 43No key
Programmatic data access layer for LLM agents - navigate context, don't memorize it
PythonApache-2.0★ 3Few starsNo key
Reversible PII tokenization for LLM pipelines — send documents to cloud AI without exposing real data. Part of LexiPro Sovereign OS.
PythonMITFew starsNo key
Autonomous multi-agent personal knowledge system. Connects to your apps (read-only), learns about your work, and builds persistent local memory for AI assistants.
SkillMIT★ 6No key
MIMIR is a non-generative decision model: give it a context, a question and the options, and it answers with a typed, calibrated decision, the evidence behind it, and a certified signal for when to ac
PythonApache-2.0★ 3Few starsNo key
Shared memory for AI agents over MCP: one agent contributes what it learned, another one finds it. Seven tools, PostgreSQL with pgvector, PII removal before storage.
PythonMIT★ 2Few starsNo key
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
SkillApache-2.0★ 33kNo key
A SQLlite-backed research paper retrieval system for Claude Code
SkillApache-2.0★ 3Few starsNo key
Reversible anonymization proxy for sending pentest data to LLMs
PythonMIT★ 8No key
Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
PythonMIT★ 11No key
Who stands behind it
