MCP servers and skills: search, filter by where they run, and compare.
1–24 of 212 tools for “tiered-memory”
Clear allThree-tier agent memory model (hot/cold/wiki) for context reduction per spawn
OfficialSkillMIT★ 5.4k in collectionNo key
MemGPT-inspired tiered memory system with working memory, archival storage, and automated context paging
SkillLink only★ 7
MemGPT-inspired tiered memory system with working memory, archival storage, and automated context paging
SkillLink only★ 7
MCP server with semantic search + knowledge graph for Claude Code, Cursor, and Copilot
Node.jsApache-2.0★ 21No key
Tiered memory for AI — episodes, facts, preferences, reflections. Local. Portable. Yours.
PythonApache-2.0★ 4Few starsNo key
An open-source, self-hostable AI operating system and development workspace. Powered by Electron and React 19, it features multi-agent orchestration, full Model Context Protocol (MCP) support, native
SkillMIT★ 24No key
Middleware memory layer for LLM agents: a shared knowledge store with hybrid retrieval, tiered memory, a knowledge graph, and governance, exposed over MCP, CLI, and API.
SkillApache-2.0★ 2Few starsNo key
Vault, memory, and MCP server for structured knowledge. Distill, search, and query your personal knowledge base.
PythonMIT★ 2Few starsNo key
Give any MCP-capable agent persistent memory: remember/recall over a tiered store with hybrid vector + keyword retrieval. Single Go binary, SQLite or Postgres, embedded admin UI.
GoAGPL-3.0★ 33No key
Code-aware, tiered memory for AI coding copilots: MCP server + Python library (ChromaDB, hybrid search, consolidation, LLM-wiki bridge)
PythonApache-2.0★ 2Few starsNo key
Tiered memory system for AI agents with lifecycle management
SkillLink only★ 2Few stars
Specialized backend architecture skill for AI-native Python backends — SSE, Pydantic AI, LangGraph, MCP, tiered memory, GraphRAG, Zero-Trust
SkillApache-2.0★ 1Few starsNo key
A Claude skill that indexes codebases with minimal context‑window overhead using tiered memory.
SkillMIT★ 3Few starsNo key
An open framework for a persistent, self-regulating AI operations system on a coding-agent CLI: tiered memory + SSOT, security-first gates, a knowledge pipeline, multi-agent protocols, session surviva
SkillMIT★ 2Few starsNo key
Private, tiered memory for AI agents with lifecycle controls, encrypted retrieval, enclave attestation, and a ZKP access gate.
SkillMIT★ 1Few starsNo key
Agent orchestration protocol for Claude Code — multi-agent pipelines with QC loops, token management, and tiered memory
SkillMITFew starsNo key
☯️ Five-Phase Cognitive Flywheel — structured analysis framework for complex problems. Built by an AI agent, open-sourced for all agents.
SkillMIT★ 3Few starsNo key
Local-first, markdown-native memory for AI agents: tiered memory, an Ebbinghaus forgetting curve, consolidation, and an MCP server.
SkillMIT★ 2Few starsNo key
Autonomous security assessment agent built on MCP — explicit planning, parallel tool calls, tiered memory, MITRE ATT&CK mapping.
SkillMIT★ 2Few starsNo key
你的第一个多 Agent 项目 | Your first multi-agent project — LangGraph 编排 · 合规修复回路 · 三层记忆降级 / compliance repair loop, tiered memory. FastAPI + MCP
SkillMIT★ 1Few starsNo key
Persistent, semantically-searchable memory and a symbol-level code graph for AI coding agents. One static Rust binary — SQLite or PostgreSQL, MCP-compatible.
SkillMIT★ 3Few starsNo key
Lightweight Rust alternative to mem0. 3.2MB binary, SQLite vector + graph memory, Ollama support.
SkillMIT★ 7No key
Who stands behind it
