Local-first AI agent memory daemon. One command, works offline, no account. Markdown storage, hybrid search (SQLite FTS5 + embeddings), MCP protocol, web dashboard.
Shared, structured memory for AI coding agents — MCP server + CLI. One memory layer for Claude Code, Codex, Cursor & every MCP client.
A desktop search engine for everything you write, read, and keep. Connect your Obsidian vault, projects, Calibre library, and code repos, then find anything with local hybrid search and expose through
Vault-native MCP server for Obsidian: let Codex, Claude Code, Hermes, and other agents read, search, and safely manage your notes.
Headless semantic MCP server for Obsidian, Logseq, Dendron & any markdown vault. AST-based surgical editing, hybrid vector + TF-IDF search, zero-setup local embeddings — no app or plugins required. St
Long-term memory for your AI agents, in your own AWS account. Notes, decisions and code in one store that Claude, ChatGPT, Codex and other MCP clients search, with a source pointer on every result. Pe
Persistent visual memory for AI agents — capture screenshots, embed with CLIP ViT-B/32, compare, recall. MCP server + Rust core library.
MIT-licensed agent framework for the AxisVela ecosystem: governed agent loop, model/tool/memory/event primitives, plugins, sandboxing, and policy.
AI-powered codebase intelligence platform — MCP Server, AST analysis, Knowledge Graph, and semantic memory with SQLite + sqlite-vec. Analyze any codebase in minutes.
Open-source MCP server for your docs. Zero LLM at query time. docker compose up and go.
Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.
Local-first memory for AI assistants. Keep preferences, decisions and lessons across sessions and connected tools in readable Markdown files.
MCP-powered memory, policy, and experience layer for safer AI agents.
A database engine purpose-built for AI memory. Native Go · Provenance-aware · Revocable · Embedded
Persistent memory for AI coding agents via MCP: a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter and Gemini Flash into Neo4j vi
AI-powered MCP marketplace enabling AI engineers to deploy, monetize, and scale MCP tools using a pay-per-task execution model with integrated Stripe and Web3/crypto billing.
One memory for all your AI tools. Local, private, and always up to date. Works with Claude, Cursor, Ollama and any MCP app.
Point a cross-model AI engineering team at your own codebases. The Agent OS keeps named AI maintainers' identity, memory and review across labs alive between sessions — the Brain Neo.mjs runs on itsel
MCP server with 40 tools for AI agents. Memory, web fetch, search, file ops, screenshots, and multi-agent coordination in one Go binary.
Persistent semantic memory server for MCP - Give your AI long-term memory that survives across conversations. Lightweight Python server with SQLite storage and semantic search.
Local-first agent memory in one SQLite file: sqlite-vec/QJL two-pass vector + FTS5 search, knowledge graph (optional auto capture,) Ed25519-signed entries, and MCP server. No cloud dependencies.
Persistent decision memory for AI coding agents. MCP server for Claude Code, Cursor, Cline.
MCP server for Windows memory forensics. Provides AI agents with 33 tools for analyzing memory dumps using Volatility 3, MemProcFS, and CLR/SOS backends. Includes process analysis, malware detection,
MCP server for Google's free public Knowledge Graph Search API - search for structured entity information about people, places, organizations, and concepts
MCP server exposing NaN API media tools: image generation/editing (flux-2-klein), TTS (kokoro), STT (whisper), embeddings and rerank
Huntable CTI Studio is an AI-assisted cyber threat intelligence workbench that turns open-source CTI into Sigma rules.
Shared memory layer for AI agents. Deploy once, connect Hermes/Trae/Cursor/Claude Desktop via MCP - they all share one memory. $0/month on Cloudflare free tier.
Context-sharing MCP Gateway on Cloudflare
An MCP server that uses Workflowy and Claude to manage Tasks & Information in Workflowy and create a Second Brain
flashmind — Gemini 3.8 Flash Smart Agent. Gives Gemini Flash persistent memory (Engram), coding skills, and no-hallucination rules. Works in Gemini CLI, Antigravity, Cursor, VS Code, Claude Code and a
Turn social-media creators' videos into a searchable, curated knowledge base — Next.js download/manage app + GPU transcription (faster-whisper) + RAG
MCP server for turning Siyuan into an AI-native, automation-ready knowledge base.
Semantic search MCP server for Claude Code conversations. Hybrid vector + keyword search across all your sessions, fully local.
MCP server and CLI for discovering and installing AI coding assistant capabilities — skills, agents, and tools — via semantic search and one-command setup.
Self-hosted semantic code search MCP server for Claude Code, Cursor, Codex and Copilot. Indexes many repos locally with tree-sitter AST chunking, a symbol graph (find usages) and git history, on Qdran
Lightweight RAG server for the Model Context Protocol: ingest source code, docs, build a vector index, and expose search/citations to LLMs via MCP tools.
पूरी डायरेक्टरी
RAG, ग्राफ़ और एजेंट की लॉन्ग-टर्म मेमोरी। 2,640 सर्वर, सबसे ज़्यादा इस्तेमाल वाले पहले। हर एक पब्लिशर का पेज खोलता है।