CodeGrok MCP is a Model Context Protocol (MCP) server that enables AI assistants to intelligently search and understand codebases using semantic embeddings and Tree-sitter parsing.
One memory, every terminal — a shared memory layer for any MCP client.
MCP server for ProjectionLab — export, snapshot, and restore financial plans with a built-in FIRE advisor knowledge base.
Does your AI-generated sound match the prompt? Local QA for generative audio — check, rank, QC, picture-fit and library search with EmbeddingGemma 2. CLI, web workbench, MCP server.
Your agent can read git log. It can't read the shell commands you tried that failed. NexusMem indexes shell history with exit codes, git commits and diffs, and project docs into a local SQLite databas
DAG-based Lossless Context Management for Claude Code. Every message preserved, summaries cascade as a DAG, patterns extracted via Lossless Dream — full recall and reflection across sessions.
Any brain, any agent. Package an AI agent's brain — persona, MCP stack, skills, memory, config — into one open, signed bundle and install it into any framework (OpenClaw, Hermes, Claude Code) in one c
Local, searchable project memory for AI coding agents. Markdown source of truth, MCP interface, safe structured updates — no cloud.
Bring Semantics to your AI Agents via the OpenMetadata & Collate AI SDK
Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.
Structured local memory storage and retrieval for LLM agents
Ai智能医生聊天助手-这是一个前端基于Vue3、TS、后端基于Nest.js、MongoDB、Redis、Milvus并结合大模型、RAG等技术实现的医疗库智能问答系统,能结合大模型的生成能力和上传的专业医疗领域知识库针对提问给出专业回答。同时具备工具调用能力,可使用MCP集成网页爬取能力让大模型根据网址对应的医疗领域文章进行分析和输出。
Persistent local memory for Claude, Cursor & Codex. 21 MCP tools, hybrid retrieval (BM25 + vector RRF), bi-temporal queries, contradiction detection. SQLite + Knowledge Graph. No cloud, no API keys. n
Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief revision, selective forgetting, and reproducible benchmarks.
Persistent project-aware memory for AI coding tools. Built on MCP. Works with Codex, Claude Code, and other MCP-compatible clients.
A minimal graph engine for grounded AI — records, associates, and retrieves, but never invents. Written in Rust.
MCP server giving AI coding agents accurate Siemens NXOpen .NET API knowledge via hybrid retrieval (BGE-M3 + sqlite-vec), built from your own licensed NX installation
Persistent semantic memory for AI agents on Raspberry Pi 5 — local Qdrant + MCP, no cloud, ~3s per query
Zero-bloat distributed vector memory, hardware-enforced domain firewalls, and NAT-traversing execution mesh for multi-instance Hermes agent fleets.
A Retrieval-Augmented Generation (RAG) Model-Controller-Provider (MCP) server designed to assist AI agents and developers in understanding and navigating codebases.. It supports incremental indexing a
A context-guardian CLI for MCP servers. It provides access to MCP servers via CLI and returns clean, structured summaries to the AI agent. This prevents context window overflow and preserves the agent
Your AI memory as a local folder you own. Claude, Codex, Cursor and any MCP app share it; you see every change and can undo it.
AI context engine for Power BI models — turns .pbit/.pbip (TMDL) into indexed, queryable context for LLM agents (MCP server, CLI, docs). Zero dependencies.
The Python Package Manager (PPM) with persistent memory MCP tools inside Contextplus supermodeltools and context7
Agent memory for Claude Code, Cursor, Codex: MCP server + Graph RAG over your Obsidian or markdown notes, a search layer for a Karpathy-style LLM Wiki. Wikilinks are the graph, SQLite the only store.
MCP server that uses Gemini's context caching as extended memory for AI assistants. Load GitHub repos, URLs, PDFs.
A lightweight, local-first persistent memory server for AI tools. Stores structured memory entries in SQLite and exposes them over both the Model Context Protocol (MCP) and a plain REST HTTP API
Zero-infrastructure, local-first memory for AI agents. One SQLite file — no Postgres, Neo4j, or cloud. Bi-temporal supersession (updates, never deletes), four-channel hybrid retrieval, and a drop-in M
Local-first semantic code search for repository annotations via GGUF embeddings and sqlite-vec.
MemoryVault — a self-hosted, graph-aware memory server for AI assistants. Cloudflare Workers + D1 + MCP.
An AI-native CLI Tool and MCP server for .NET memory dump investigations. Leverage LLMs (Claude/Gemini) to analyze heaps, threads, and exceptions using natural language. Built with ClrMD, token-eff
Persistent memory for AI coding agents. SQLite-backed knowledge graph with MCP server.
Medha is a Model Context Protocol (MCP) server that provides persistent, git-versioned memory storage for LLM applications. It combines the power of Git's version control with graph-based memory assoc
Local-first multi-engine AI agent dashboard — Claude Code, Codex & built-in ReAct in one window. MCP support, skills auto-loading, long-term memory. No account, no relay.
Engram-inspired memory MCP server with hot cache and pattern mining
Proof-backed, drift-resistant AI memory for your codebase. 11 languages, 28 MCP tools, evidence-linked claims.
Toàn bộ thư mục
RAG, đồ thị và bộ nhớ dài hạn cho agent. 2,637 máy chủ, dùng nhiều nhất xếp trước. Mỗi máy chủ mở ra trang của nhà phát hành.