Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.
Persistent 6-DoF SE(3) spatial world state, object trajectories, and affordances for robotics.
Semantic search over Handsontable and HyperFormula docs, API reference, release notes, and issues.
Self-hosted OAM memory with cited recall over your existing deployment
Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.
BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.
SocratiCode — MCP server for local codebase indexing, semantic search, and code dependency graphs. All private, all local via Docker.
Persistent memory storage and retrieval for AI agents through the hosted HeurChain MCP service.
Local RAG MCP Server - Easy-to-setup document search with minimal configuration
MCP distribution SDK. Build sales funnels, lead generation, booking, and quote apps on top of your MCP server. Event tracking, flows, widgets, knowledge base.
Audit net MCP context avoided per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients
Read, search and track your RSS feeds: semantic search, story clustering, watches, OPML import.
Enterprise Knowledge Base CLI, MCP, and current-Agent installer
MemDrive — an MCP server that gives LLMs persistent memory on local sync folders. Local filesystem backend, zero native dependencies.
Self-hosted Markdown knowledge base with a web UI: search, read, create, edit, tag and template notes.
Persistent memory MCP server for AI coding agents
KnowMan MCP server: search, ask, save and read your Knowledge Base from any MCP client.
Recall personal AI knowledge base MCP server: save URL, create note, add tags to card.
Zibby Memory MCP Server — exposes test history via Dolt to AI agents
Learning assistant extension for DeepSeek Harness (dsh) and Claude Code (MCP): DeepTutor tutoring for your agent: deep explanations, self-test questions, learning paths, personal knowledge-base search
Local-first agentic memory: the engram MCP server launcher. Memory + knowledge graph + beliefs + code intelligence for any MCP client.
Fast, local, low-token long-term memory for AI coding tools (Claude Code, Kiro, VS Code, Cursor, OpenCode) over MCP.
Read the MindForge engine over MCP: knowledge graph, project health, and audit log.
Structural Thinking Engine: MCP server integrating Gemini CLI with authentic creative processes, structural observation protocols, and persistent memory charts based on Robert Fritz's methodology
Reactome MCP — open biological pathway knowledge-base.
Your Obsidian vault is Claude's memory — local semantic search over your notes via MCP, always fresh, never reindex.
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
Pay-per-call NLP & embeddings APIs on Base via x402. No keys/signup; agents pay per call in USDC.
Local, privacy-focused RAG service for code search via MCP. https://linggen.dev
Search and manage your Dexi notes: full-text and semantic search, tags, folders, spaced repetition.
Anti-poisoning memory for agents: provenance, conflicts, quarantine gate.
MCP server for interacting with Pinecone vector database
Speech denoise, transcripts (SRT/VTT), embeddings, reranking, entities and translation.
Encrypted Markdown notes and team knowledge base. Search, read and write notes in vaults you allow.
Heartwood Memory — governed AI agent memory; signed provenance. BUSL-1.1; not OSI open source.
Gesamtes Verzeichnis
RAG, Graphen und Langzeitgedächtnis für Agenten. 2,590 Server, die meistgenutzten zuerst. Jeder öffnet die Seite des Herausgebers.