Turn a folder of code/docs/papers into a queryable, persistent knowledge graph for AI coding assistants.
MCP server for Naumu - access your knowledge graph from Claude Code, Cursor, and other AI coding agents
O(1) routing, semantic search, and quality-filtered demand-driven experiences over 800+ records.
CPU task-specific context preparation and explicitly saved local project notes through MCP.
Mimir long-term memory for OpenCode sessions
Local long-term memory for Claude Code and other agents: every message kept word for word, no cloud.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Convert a codebase into a local AST knowledge graph that gives coding agents structural context for navigation and refactoring.
Official HTTP TypeScript & Node.js SDK for / ml (https://api.slashml.ai)
Persistent memory for Claude via weighted, interconnected knowledge nodes.
MCP server for persistent, semantic memory across AI sessions
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
SocratiCode — MCP server for local codebase indexing, semantic search, and code dependency graphs. All private, all local via Docker.
Read-only MCP server for Stet (stet.md): search and navigate the knowledge base from agents.
Cloudflare Workers AI inference: LLM chat completions (Llama, Qwen, DeepSeek), BGE text embeddings and Flux image generation.
Fast, local, low-token long-term memory for AI coding tools (Claude Code, Kiro, VS Code, Cursor, OpenCode) over MCP.
Associative memory for LLM agents — a key-graph memory layer (MCP server) that recalls by association, not just vector similarity. A graph-based alternative to vector-store agent memory.
Save up to 80% tokens when AI reads code — MCP server for token-efficient code navigation, AST-aware structural reading instead of dumping full files into context window
Atlaso, the AI memory layer: one shared, persistent memory for every AI tool you connect.
Local semantic search for your documents. Index Markdown, PDF, and Office files with hybrid BM25 + vector search.
Chipp: a project's memory, circles, and scheduled tasks
npm wrapper for the Code Knowledge Graph CLI (ck)
Agent memory with no API key, no LLM, and no embedding provider. Serves MCP over stdio against a local SQLite store, or Cloudflare Workers + D1. Drop-in for @modelcontextprotocol/server-memory; every
Persistent memory for AI coding agents: the next session starts where the last one left off. Works with Claude Code, Codex, Cursor, OpenCode and more.
Semantic code & doc search with keyword boost. AST code nav, auto HF mirror, local, privacy-first.
Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking
Persistent memory for AI tools. Local-first knowledge graph with hybrid search.
Windows AgentMemory downstream for Codex with project-scoped persistent memory, bounded cross-project recall, and an authenticated loopback MCP service; prebuilt Windows releases are available as an u
Local-first agent memory and knowledge base: hybrid dense and BM25 retrieval, document and webpage ingestion and optional RAG answers via local Ollama.
Local long-term memory for terminal coding agents: blueprints, code anchors and distilled lessons in one JSON file, restoring project context across sessions.
Local-first personal memory that distills Feishu/Lark chats and Claude Code/Codex sessions into a private knowledge graph of people, projects and tasks.
Persistent memory with knowledge graph visualization, semantic/hybrid search, cloud sync (S3/R2) and cross-session context management.
EtherPK Headless Client: an MCP server over a synced knowledge graph, run beside the agent on the user's own machine.
Persistent knowledge layer for agents: knowledge base, investigation threads and a journal with multi-agent attribution, on SQLite, PostgreSQL or Supabase.
Waku Memory for your coding agent: the plugin files, plus one-time history import and full record.
Desktop app that captures screen activity, stores AI summaries and OCR text locally, and exposes the history via semantic search and a timeline.
पूरी डायरेक्टरी
RAG, ग्राफ़ और एजेंट की लॉन्ग-टर्म मेमोरी। 2,653 सर्वर, सबसे ज़्यादा इस्तेमाल वाले पहले। हर एक पब्लिशर का पेज खोलता है।