• Picks
  • Discover
  • Alternatives
  • About

© 2026 Willet

  • Newsletter
  • About
  • FAQ
  • Terms
  • Privacy & Cookies
Join the Discord (opens in a new tab)
AgentScope-AI avatar

ReMe

Local-first Markdown memory workspace shared by AI agents

  • Agent frameworks and tools
View on GitHub
Website

What it is

ReMe is a memory kit that stores agent conversations and resources as plain Markdown files with frontmatter and wikilinks, then gradually distills them into a daily log and a durable knowledge base. Retrieval combines BM25, optional embeddings, and link expansion to pull relevant passages without loading everything into context. Developers wiring memory into personal assistants or coding agents can connect through a Python API, CLI, HTTP, MCP, or plugins for runtimes such as OpenClaw and Hermes Agent, and a browser studio lets people inspect and edit the memory graph.

Images

Facts

Stars
3,657 GitHub stars.
3,657

Forks
319
Commits
1,097
Contributors
38
Language
Python
License
Apache-2.0
Last commit
Oct 19, 2026
On GitHub since
August 2024
First release
September 2025
Platforms
web, CLI, self-hosted, library
Self-hostable
Yes
Tags
  • mcp-server
  • markdown
  • ai-memory
  • context-engineering
  • knowledge-base
  • rag

Last synced from GitHub on Oct 20, 2026

The 10 best overlooked open-source projects, every Monday.

Share and more

Comments

No comments yet. Start the conversation.

Similar projects

  • Volcengine avatar

    OpenViking

    Filesystem-style context store for agent memory, knowledge, and skills

    40.4k
  • Topoteretes avatar

    Cognee

    Knowledge-graph memory layer that gives AI agents long-term recall

    32.6k
  • supermemory avatar

    Supermemory

    Memory and context layer that gives AI agents and assistants recall

    31.3k
  • Fabio Akita avatar

    ai-memory

    Shared long-term memory and handoffs across AI coding agents

    11.8k