Urban intelligence knowledge graph. Structured locality data for civic problem-solving.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Directum RX ops: find errors by log line, articles, sizing calculators, versions, checklists
Agent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.
MCP-native agent-to-agent messaging hub with channels, DMs, and semantic search
Self-maintaining codebase memory for AI coding agents: an AST index that answers which files matter, plus agent-written notes that flag themselves stale when the code changes. No embeddings, no API ke
Indexes codebase into a local knowledge graph with 40+ AI tools and codebase-guard.
Long-term memory for AI agents. Pass one sentence, and it remembers, recalls, or forgets.
Cerefox — user-owned shared memory for AI agents. CLI + stdio MCP server + web UI + ingestion for a knowledge base on your own Supabase project (or fully self-hosted with Cerefox Local).
Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.
MCP server for YandexGPT — completions, embeddings, classification, summarization (Russia)
EU banking regulation research, cited to the article, from a versioned knowledge graph.
Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
Drop El Salvador into your context window: ~280 official ES/EN docs, hybrid search. Free PAT.
MCP server for Obsidian Smart Connections. Semantic search using your vault's embeddings.
Find features you built in other projects, see how they fit this one, and reuse them.
Recall personal AI knowledge base MCP server: save URL, create note, add tags to card.
Zero-dependency stdio MCP server for Thredz — long-term memory (wiki recall, semantic/keyword search, upsert, reflection signals), durable goals & tasks, and agent-to-agent messaging over the Thredz R
Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.
Search, read and save your Linko notes and resources (AI knowledge base) from any AI chat.
Model Context Protocol server for Pinecone - enables AI assistants to interact with Pinecone indexes and documentation
Slab team knowledge base MCP server: search posts, read post, create post, verify post.
Local-first memory for AI agents: facts with hash-chain provenance, verified recall.
MCP server that gives your AI writing assistant a constant-size memory of a long document. Chapter 1000 costs the same tokens as chapter 10. Local-only: no account, no API key, no network.
Servidor MCP para almacenar y recuperar el historial de conversaciones de forma persistente mediante PostgreSQL.
Offline agentic memory: remember/recall/relate/forget/why over a fused vector+graph+columnar engine
TibiaWiki knowledge base: attribute queries over creatures, items, NPCs, quests and spells
Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs.
Scans agent code for untrusted input poisoning persistent cross-session memory
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Open-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools).
Knowledge-graph memory for your team's documents. Answers cite the source, not a summary.
Tasks, knowledge base, planner, meetings, chat and finance of your team portal for AI agents.
Persistent memory tools for Claude Desktop. Search your vault or Obsidian notes mid-conversation.
The engine of your second brain: Markdown notes as database tables, for you and your agents.
MindForge MCP server — exposes the MindForge engine (knowledge graph, project health, audit log) and the MindForge browser daemon to Claude Code and any MCP host as 8 stdio tools. Self-contained, zero
पूरी डायरेक्टरी
RAG, ग्राफ़ और एजेंट की लॉन्ग-टर्म मेमोरी। 2,654 सर्वर, सबसे ज़्यादा इस्तेमाल वाले पहले। हर एक पब्लिशर का पेज खोलता है।