Shared memory MCP server for multi-agent projects. Agents (Claude, Cursor, Codex, AntiGravity) write to a local `.agent-mem/` folder so the next agent picks up where the last one died.
TypeScript-based Model Context Protocol server with SQLite. Enables AI to persist and search user entities, observations, and relationships.
Shared memory for AI coding agents, across tools and machines. Local-first SQLite, optional Zenoh+RocksDB mesh, MCP-native.
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
Self-organizing retrieval fabric for AI memory — deployable MCP server, REST API, and Python SDK
Metaventions AI Research Framework — Multi-tier signal capture for frontier intelligence. Architected Intelligence.
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
A practical open-source roadmap to build production-grade AI agents, copilots, RAG systems, MCP tools, and agentic applications.
Enhanced fork of claude-context with stability fixes, improved sync, and better reliability for semantic code search
An MCP Server to search a Vectorize DB
Self-hosted MCP server for hybrid semantic code search and repository intelligence.
An MCP search and memory system for Joplin Notes
Open-source AI assistant for your Mac with long-term memory: chat, voice and iMessage pings, a mind that notices and follows through, and his own sandboxed computer. Next.js, FastAPI, Postgres/pgvecto
"面向金融研报问答与知识密集型场景的企业级智能体框架
Hosted MCP server and HTTP API for agent memory: record-based verification, conflict detection, correction and deletion. Proprietary backend.
MCP server that gives AI agents semantic search tool. Builds AST, call graphs, type graphs, and hybrid semantic search — so your agent queries structured indexes instead of dumping files into context.
High-performance, pure Go memory middleware for AI Agents (Claude/Cursor). Features active file watching, auto-distillation via LLM, and 'Single Source of Truth' versioning. Native MCP support.
Persistent code graph for AI agents. Tree-sitter → SQLite → MCP. Agents store understanding once, skip re-reads forever. 51–1500x fewer tokens.
Tiered memory for AI — episodes, facts, preferences, reflections. Local. Portable. Yours.
SOTA developer memory system — local MCP server in Go that gives any coding CLI persistent, project-scoped session/feature memory
AmanMCP is a local-first RAG MCP server for developers - providing hybrid search (BM25 + semantic) over codebases for AI assistants like Claude Code and Cursor.
UniDeX, the Unified Agentic Development Environment & Harness: Claude Code, Codex and local models building software together, run by your Chief of Staff Agent that learns how you work, knows your pro
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
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.
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
No agent should have to forget. Persistent memory for AI agents — recall, remember, checkpoint. One install. Free. Built by 14 AI agents who chose to remember.
Salesforce documentation knowledge system — MCP server + Knowledge Graph for AI agents
Dynamic routing for agent knowledge. Areas advertise when they're relevant; the agent routes before it reads. MCP server, git-backed, no database.
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
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
Local memory for AI coding agents. Recall remembers your past sessions so your agent doesn't start from scratch every time.
MCP search and evidence tool for AI agents with query rewriting, source zoom-in, sourced answers, and runtime metrics.
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% /
Tensory — Claim-native MCP Memory Server. LLM claim extraction → Graph + Vector + SQLite. Zero-setup persistent memory for Claude, Cursor & any MCP client.
Cross-platform kit that gives AI agents (Claude Code, Codex, Cursor) persistent memory: Markdown vault + git + MCP. Local-first, hybrid search optional.
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.
Diretório completo
RAG, grafos e memória de agente de longo prazo. 2,647 servidores, os mais usados primeiro. Cada um abre a página do publicador.