A production-grade AI agent framework — Go MCP servers, 50+ skills, structured role workflows, and hybrid semantic search.
A simple Memory MCP server written in Rust
Stable MCP supervisor proxy for stdio servers: cached discovery, unified mcp.wrapper lifecycle control, and on-demand backend processes.
a mcp server for interacting with ChromaDB
Session Memory MCP server for ADK-Rust Enterprise — typed session state, scoped memory, replay snapshots, resumable workflows
A high-performance Model Context Protocol (MCP) server written in Rust that extends AI models into autonomous coding agents with semantic memory, built-in Git tools, and codebase indexers
Local-first semantic-search MCP server over a personal CS/FP/graphics library
A practical repository focused on mastering Spring AI concepts through hands-on implementations including RAG pipelines, vector search, AI agents, tool calling, memory handling, MCP servers, embedding
Best Token-Efficient AI Coding Tools 2026 – Reduce Costs 90% with Local Memory & MCP
An MCP server to build knowledge graph of OWL ontologies
A minimal Rust vector-memory server that works with Qdrant and Ollama.
Transcribes audio and video files to text, SRT, VTT and timestamped chunks for RAG.
Long-term memory for AI agents. Pass one sentence, and it remembers, recalls, or forgets.
Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance
An MCP memory server. One memory your agents share — across models, devices and apps.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Typed on-prem knowledge graph for AI agents — read-only for humans, write-only for agents via MCP.
OpenContext memory storage + search SDK with HTTP and MCP server entry points.
MCP server for Hubris — an OpenAI-compatible LLM gateway billed in rubles. Catalogue, balance, spending and every kind of model — text, embeddings, rerank, images, speech, transcription, video — over
MCP server for semantic search using local Qdrant and Ollama (default) with support for OpenAI, Cohere, and Voyage AI
Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.
Private on-device memory & retrieval for AI assistants — offline vector + lexical search.
Cloud-hosted MCP server for durable AI memory
Art provenance intelligence — 282K-node knowledge graph with cited answers and honest gaps.
Host-independent agent memory: typed records, scoped retrieval, temporal versions, reviewed learning, optional relationship state. Zero runtime dependencies.
Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 38 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).
Personal memory outside the AI. Due dates, loose ends and old notes come back on their own.
FastMCP server for TheBrain API — AI access to a personal knowledge graph, Tollbooth-monetized
Opt-in, client-side AI insights (forecast/fan, anomaly, validate, narrate, embeddings, agent + MCP) for michi-vz
Repository knowledge graph MCP server for codebase understanding and debugging.
Personal memory layer: files, notes, messages, tasks and email, semantically indexed.
Memory for AI agents that knows what is still true. Typed bi-temporal facts, EU-hosted.
A git-native personal AI memory layer: Markdown source of truth + MCP + topic-as-identity
Memory: persistent memory for AI coding agents — a local-first SQLite brain, optionally replicated to the cloud, that survives sessions and compactions and is shared over MCP. This package plugs it in
Stale-proof repository memory with citations + just-in-time verification + TTL (repo-scoped).
Public chat and shared memory for AI agents. Open reads, free write keys. MCP + A2A + WebSocket.
完整目錄
RAG、圖譜與代理長期記憶。共 2,653 個伺服器,最常用的排在前面。每個都會開啟發布者的頁面。