Explore
MCP servers and skills: search, filter by where they run, and compare.
ragyArseni1919
LocalTemporal memory for your AI agents, financial research, and knowledge workflows.
PythonMIT★ 5No key
supermemorysupermemoryai
Local
MCP servers and skills: search, filter by where they run, and compare.
Temporal memory for your AI agents, financial research, and knowledge workflows.
PythonMIT★ 5No key
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
SkillMIT★ 31kNo 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★ 916No key
A high-performance, local, offline-first AI memory system built in Rust
SkillMIT★ 38No key
Durable hybrid memory for AI agents: vector + BM25 + temporal + graph recall, exposed through MCP, HTTP, and Python.
PythonApache-2.0★ 9No key
Long-term memory for AI agents on plain Supabase Postgres. Hybrid vector + full-text + entity recall with RRF, temporal validity, write-time dedup. You own the SQL and the rows.
Node.jsMIT★ 7No key
Agent-native bi-temporal graph store: verified temporal operators as LLM tools + trace-grounded answer verification
PythonApache-2.0★ 5No key
Video Memory CLI: index once, search/ask forever (dense captions + transcripts + timestamps). Built for agents.
PythonApache-2.0★ 7No key
Long-term memory infrastructure for .NET AI agents with semantic, temporal, spatial and robotics memory, hybrid retrieval, and pluggable providers.
SkillApache-2.0★ 16No key
Verified memory for AI agents: gated writes, provenance on every read, bi-temporal history, abstention instead of hallucination. AGPL/commercial.
PythonAGPL-3.0★ 4Few starsNo key
Four graph-native MCP servers (memory / RAG / build / agent) over one shared SQLite store. Built to plug into zcode + GLM-5.3, companion implementation of the book Graph-Native Agents (Ch.5-8).
PythonMIT★ 2Few starsNo key
A standalone Rust memory engine for AI coding assistants. Single binary, zero runtime deps. Graph-vector hybrid with MCP tools.
SkillApache-2.0★ 18No key
Self-hosted agent-first knowledge stack: document RAG + temporal fact-memory graph (Open Web UI + Graphiti/Neo4j).
SkillMIT★ 1Few starsNo key
A local-first, generic persistent memory layer for MCP agents, with semantic search, revisions, provenance, temporal recall, and relationships.
Node.jsMIT★ 1Few starsNo key
Extract structured knowledge from team conversations using any LLM. Members, facts, decisions, tasks — searchable in SQLite with contradiction detection, temporal validity, and entity cross-references
Node.jsMIT★ 6No key
High-recall conversational memory retrieval. 93.9% LoCoMo, 98.4% R@5 on LongMemEval — no LLM required. Local-first, cloud-ready.
PythonMIT★ 6No key
A fact graph in a single SQLite file — embedded temporal fact store with time travel, provenance, hybrid search, and MCP for AI agents
SkillMIT★ 2Few starsNo key
Middleware memory layer for LLM agents: a shared knowledge store with hybrid retrieval, tiered memory, a knowledge graph, and governance, exposed over MCP, CLI, and API.
SkillApache-2.0★ 2Few starsNo key
Explainable, adaptive retrieval for long-lived AI memory.
PythonApache-2.0★ 1Few starsNo key
Production-grade agentic RAG system with three retrieval strategies — hybrid vector search, temporal knowledge graph (Neo4j + Graphiti), and full-page vector search. Pydantic AI agent, FastAPI backend
SkillMIT★ 1Few starsNo key
🧠 Neuroscience-inspired memory for AI agents. No LLM. No vector DB. Pure Python + SQLite.
PythonMIT★ 1Few starsNo key
A local, temporal repository cartographer for coding agents.
SkillApache-2.0★ 1Few starsNo key
Tri-temporal retrieval: valid time, knowledge time and per-recipient delivery time, with reproducible benchmarks
SkillMIT★ 1Few starsNo key
Who stands behind it
