Local-first persistent memory for AI agents over MCP. Ground truths, a failure firewall that blocks repeated mistakes (negative learning), and hybrid recall, stored in SQLite on your machine. No cloud
Detect stale source context and retain traceable code-chain understanding for AI coding agents.
Persistent, governed local memory for MCP-compatible AI clients.
Semantic search across 5 US government healthcare databases.
Self-hosted shared memory and docs for Claude Code, Codex and Antigravity agents, with a graph UI
The Bible as a knowledge graph of verses, people, places, topics and Hebrew lexemes: scripture search, interlinear lookup, cross references and genealogy.
Local-first MCP server: semantic search over library docs. No cloud, no API key, no telemetry.
An agent's long-term memory: one fact per semantic HTML file in git, four-arm retrieval, and curator sessions on a branch.
Persistent, encrypted, deterministic memory for AI agents. Local-first, 173 canonical tools.
Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
Live database schema memory, ADR workflow & AI pair programming companion
Shared local memory, decisions and approved agent tasks. Requires the installed Manwe Mac app.
Self-hosted, uncensored AI agent: ask it tasks, search its long-term memory and your documents.
Local server for memvid storage and semantic search.
ERC-8183 RAG Knowledge Base & Vector Embedding Anti-Poisoning Auditor & Escrow on Base.
Chinese-first brain-inspired memory MCP — hybrid recall, 7-layer user profile, workspace assembly.
Memory for AI coding agents. Call graphs + refactor safety + persistent code context. 35 MCP tools.
Read and change a governed, versioned knowledge graph on Postgres through typed tools.
AI that remembers. Local-first cross-session, cross-project long-term memory for coding tools.
VISEON's Schema.org knowledge graph: products, services, people, FAQs and terms, from viseon.io
A living knowledge graph to read, think against, and leave a deposit in that outlives you.
Your repo's memory, available to every AI tool your team uses. A local MCP server that turns a memory/ folder into searchable shared context.
Deterministic memory & code intelligence MCP for 15 IDEs (100% LongMemEval in 12.9ms, 0 LLM tokens).
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
Markdown memory for coding agents that audits itself: drift reports and session digests.
Cooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian)
YouTube knowledge base: summarize videos, fetch transcripts (even without captions), search channels and playlists, and save results for cross-session recall.
Give any MCP client a business's own knowledge base from a self-hosted cob-rag-engine.
Turn a website into Markdown with headings, links and word counts.
(beta) Wontopos (WOS) long-term memory as an MCP server — one memory across Claude Code, Claude Desktop, Cursor, ChatGPT, and your own agents.
Semantic search and pattern discovery for Obsidian and markdown vaults.
Memory for coding agents: stores every fix and finds it again when the problem returns. EU-hosted.
Shared second brain for any AI with agent permissions
87 public tools: agent workflows, audio data transfer, semantic search, queues and webhooks.
A searchable knowledge base your assistant reads and writes.
Local-first memory engine for AI coding agents with hybrid search, lifecycle management, and MCP support
Tüm dizin
RAG, graflar ve uzun süreli ajan belleği. 2,619 sunucu, en çok kullanılanlar önce. Her biri yayıncının sayfasını açar.