leonardsellem/hypermnesic
by Various
Git-first memory for AI agents: Markdown files are truth, the index is disposable, writes are reviewable commits.
MCP
leonardsellem/hypermnesic
Added 19 June 2026
Overview
Hypermnesic is a Git-based memory system for AI agents. Markdown files serve as the canonical data store, the search index is rebuilt from them, and every write becomes a reviewable Git commit.
Best for
Best for
Developers who need an auditable, Git-versioned memory layer for AI agents
Use cases
- Persist agent state between sessions
- Track and review AI-generated changes via commits
- Maintain an auditable, version-controlled knowledge base
How to use
Install
uv tool install hypermnesic Tools exposed
uvgittailscale
Tested with
ChatGPT, Claude, Claude Code, Codex, Obsidian
Notes
Hypermnesic is a Git-based memory system for AI agents. Markdown files serve as the canonical data store, the search index is rebuilt from them, and every write becomes a reviewable Git commit.
2 stars on GitHub. Last updated 2026-06-19. Licensed AGPL-3.0.
Use cases
- Persist agent state between sessions
- Track and review AI-generated changes via commits
- Maintain an auditable, version-controlled knowledge base
Pros
- Git-based versioning provides built-in audit trail
- Markdown as truth source keeps data human-readable
- Disposable index enables low-maintenance rebuilds
Cons
- Limited to 2 stars indicates minimal community validation
- Requires Git expertise to set up and troubleshoot
- Index rebuilds may be slow with large Markdown repositories
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Git-based versioning provides built-in audit trail
- Markdown as truth source keeps data human-readable
- Disposable index enables low-maintenance rebuilds
Cons
- Limited to 2 stars indicates minimal community validation
- Requires Git expertise to set up and troubleshoot
- Index rebuilds may be slow with large Markdown repositories
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
