내 AI에게 '나'를 기억시키는 로컬 second-brain — 결정의 선택·이유·전제를 .md 노트로 남기고, MCP로 어떤 AI 앱(Claude Code·Desktop·Cursor)에서든 꺼내 쓰는 개인 기억 계층. 전부 로컬(Ollama 임베딩)·오픈소스.
Ultra-lightweight local knowledge base (OKF v0.2 / LLM Wiki). Markdown is the source of truth; agents connect over MCP — Claude Code, Codex, Cursor, Strata, Unsloth and more.
Ultra-fast MCP server for semantic memory and code analysis
Persistent codebase memory for AI coding agents. MCP server + CLI + dashboard.
Athena MCP RAG Server: Production-ready Pinecone-powered Retrieval-Augmented Generation server for Claude Desktop, with PDF ingestion, teacher tools (explain, study plans, quizzes)
LLM readiness linter for websites. Audits robots.txt, llms.txt, Schema.org, and content density on a 0-100 scale. Includes MCP server. Published on PyPI: pip install context-cli.
API-first Markdown conversion MCP: bring your own local models or network APIs for layout, formulas, tables and text.
Nexus Memory System is a Rust memory platform for AI coding agents. It provides a shared SQLite-backed memory store, a CLI for day-to-day operations, native hook installers for supported agent tools,
SQLite-based MCP memory server with WAL mode for concurrent access. Drop-in replacement for @modelcontextprotocol/server-memory
Shared memory for AI coding agents, across tools and machines. Local-first SQLite, optional Zenoh+RocksDB mesh, MCP-native.
Local MCP server that captures the why behind your code — domain knowledge for Claude, Cursor, Copilot, and any MCP agent.
Auditable, self-improving knowledge & memory for AI agents over MCP. Zero-key & multilingual by default · citation-enforced answers · replayable why-trace · judge-gated compounding loop. Postgres-only
TypeScript-based Model Context Protocol server with SQLite. Enables AI to persist and search user entities, observations, and relationships.
A Research Cortex. A research companion for Claude. Your library, notes & memory stay on your machine; answers cited from your own library; 30+ specialist skills; auto cross-pollination across paper
Local code search and cited answers for Project Chrono and PyChrono, grounded in Chrono's own code, demos and docs. CLI, MCP server for editors, and web app; search needs no API key, written answers u
Local-first, deterministic memory store for AI agents: SQLite-backed BM25 with optional local ONNX semantic search and cross-encoder rerank, graph projection, and an MCP adapter. No required network o
SOTA developer memory system — local MCP server in Go that gives any coding CLI persistent, project-scoped session/feature memory
This repository presents a production-ready RAG system combining LangGraph agent with Model Context Protocol (MCP) integration. Features hybrid search using Reciprocal Rank Fusion (RRF) via MongoDB ve
Self-hosted, model-agnostic AI agent orchestration platform. Build, run, and observe AI agents backed by any LLM (Anthropic, OpenAI, Gemini, Ollama). Features: agent groups/pipelines, tool execution
VecRecall 是一个进化版的 AI 长期记忆系统, v2.0 在纯向量检索之上,叠加 LLM 认知层(写入时自动抽取实体/关系/摘要/话题 + 语义去重)、时序知识图谱、遗忘曲线与主动蒸馏、多跳向量+图谱混合检索与静态加密,并把嵌入升级为「零依赖 subword 词法 + 多语言语义模型」双层。内置可复现评测集(21 组中英混合 query)中,召回率(R@5)达到 语义嵌入 100% /
20 free production-ready domain skills for Claude Code, Antigravity & AI agents — LangGraph, RAG, GEO/AEO, MCP, security
Persistent, local-first memory for AI agents. Selective by design: filters what's worth keeping, links what's related, and says nothing when it doesn't know. SQLite + ONNX, no cloud, no API keys.
Archivist MCP is a local-first memory server for coding agents. It persists decisions, incidents, rules, entities, and graph relationships in SQLite, then exposes them over MCP (stdio/HTTP), SSE team
On-prem, MCP-native memory for AI agents in regulated settings: every write lands in a SHA-256 hash-chained log an auditor can check offline, without running the vendor's code. Rust, embedded, Apache-
MCP search and evidence tool for AI agents with query rewriting, source zoom-in, sourced answers, and runtime metrics.
Long-term memory for AI agents. MCP server with local embeddings, heat-based recall, and hierarchical clustering on embedded SurrealDB.
Local hybrid search over your own files — dense vectors, BM25, and metadata filters in one query. The same binary is an MCP server, so agents can search your notes.
MCP Server for Agentic RAG applications
Semantic code search MCP server for Claude Code — find code by meaning, not just text matching
Persistent memory for AI coding agents. MCP server + lifecycle hooks that give Claude Code, Codex and Cursor long-term memory across sessions — one Rust binary, one local SQLite database, no server.
A practical open-source roadmap to build production-grade AI agents, copilots, RAG systems, MCP tools, and agentic applications.
Memro — the memory layer for AI context. Server, SDKs, MCP server and integrations.
A semantic search system for Markdown notes with Model Context Protocol (MCP) server integration. Build searchable embeddings indexes from your Markdown files and expose them via JSON-RPC 2.0 over std
Self-hostable, open-source shared memory for AI agents: plain markdown in git that a curator agent organizes itself, readable and writable over MCP. Beta — no auth, single machine.
Rust-native universal retrieval layer for humans and AI agents — search, extract, rank, and synthesize the web. CLI + REST API + MCP server, with adaptive extraction (CEP), token-budgeted packing, mul
AI Books MCP Server - Extend LLM context 15-60× via gravitational memory | Official MCP server for Claude Code & Anthropic
Toàn bộ thư mục
RAG, đồ thị và bộ nhớ dài hạn cho agent. 2,638 máy chủ, dùng nhiều nhất xếp trước. Mỗi máy chủ mở ra trang của nhà phát hành.