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.
PineScript v6 MCP Server - 6 tools for docs lookup, code validation, and code generation. 1751 entries, 100% local.
Self-hosted MCP memory server with hybrid semantic + keyword search on Cloudflare Workers
A powerful knowledge management system that forges wisdom from experiences, insights, and best practices. Built with Qdrant vector database for efficient knowledge storage and retrieval.
Local MCP server + CLI turning YouTube & local audio into rich sonic signatures. Extracts BPM, section-by-section key, vocal presence, transient punch, and 512-dim CLAP vibe embeddings. Powered by De
Persistent code graph for AI agents. Tree-sitter → SQLite → MCP. Agents store understanding once, skip re-reads forever. 51–1500x fewer tokens.
Persistent memory and identity for AI minds, served as MCP tools on Postgres.
A MCP (Model Context Protocol) server that exposes primitives for interacting with a Knowledge Graph
GhostMem — a local-first MCP memory server for Claude Code, opencode, Cursor, and other MCP clients.
RDF knowledge graph for LLMs — an MCP server with 5 tools: triple, sparql, graph, search, validate
Local-first AI context engine combining a structural Atlas, verified Archive, episodic Animus memory, CLI, MCP, and focused context routing.
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
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.
RedM / RDR3 docs MCP server: native lookups, semantic search, VORP, RSGCore, oxmysql.
Shared memory for AI coding agents, across tools and machines. Local-first SQLite, optional Zenoh+RocksDB mesh, MCP-native.
TypeScript-based Model Context Protocol server with SQLite. Enables AI to persist and search user entities, observations, and relationships.
SQLite-based MCP memory server with WAL mode for concurrent access. Drop-in replacement for @modelcontextprotocol/server-memory
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
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
Local MCP server that captures the why behind your code — domain knowledge for Claude, Cursor, Copilot, and any MCP agent.
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.
Token-efficient code intelligence for AI agents — 66 MCP tools via tree-sitter AST, BM25F search, semantic search, and LSP bridge
SOTA developer memory system — local MCP server in Go that gives any coding CLI persistent, project-scoped session/feature memory
Native Rust code intelligence for repository navigation, change review, impact analysis, and code health, backed by per-project RocksDB.
Ultra-fast MCP server for semantic memory and code analysis
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
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
Code intelligence MCP server for Claude Code — multi-project code graph, semantic search, session history, knowledge base
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.
The Compiler-Aware Operating System Kernel CodeGraph Engine for Token-Efficient Structural Codebase Retrieval
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% /
A local-first, token-efficient MCP memory server for AI coding clients
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
Semantic search over WSO2 docs (APIM, IS, MI, Choreo, Ballerina) via RAG and pgvector.
MCP search and evidence tool for AI agents with query rewriting, source zoom-in, sourced answers, and runtime metrics.
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.
Tüm dizin
RAG, graflar ve uzun süreli ajan belleği. 2,610 sunucu, en çok kullanılanlar önce. Her biri yayıncının sayfasını açar.