Launching today

Levh

Launching today

Local-first memory for AI agents and workflows

2 followers

Local-first memory for AI agents and workflows

2 followers

•

•

LEVH is a local-first memory layer for AI agents and human. It captures context from conversations, projects, files, email, calendars, and MCP tools; builds an inspectable knowledge graph; surfaces trust and conflict signals; and lets stale details fade—without cloud accounts or telemetry.

Free

Launch tags:Productivity•Open Source•Artificial Intelligence

Launch Team / Built With

Viktor.comAn AI coworker that actually does the work

Promoted

Maker

📌

I built LEVH because AI tools keep losing the context that makes work coherent: decisions, commitments, people, project conventions, and information that changed last week. LEVH is a local-first memory layer for AI agents and workflows. It captures and connects context from conversations, projects, files, email, calendars, and MCP-compatible tools—then makes it inspectable through a knowledge graph, trust signals, reviewable conflict candidates, and memory decay. The goal is not another transcript archive. It is durable, self-curating context that stays on your machine: no cloud account, telemetry, Redis, or managed database required. Quick start: pip install levh levh setup --demo --client claude --profile work levh serve I’d love feedback from anyone working with AI assistants, personal knowledge workflows, MCP tools, or multi-agent systems: what context does your AI forget most often?

Report

11d ago

Maker

Thanks so much to everyone checking out LEVH today! 🙏 Building this has been a labor of love — if you try the quick start, I'd genuinely love to hear what breaks, what surprises you, or what memory problem you wish it solved. Every comment and upvote means a lot on launch day!

Report

5h ago

Forum Threads

p/levh

•

1d ago

Levh — Local-first memory for AI agents and workflows (launching soon on PH!)

Hey everyone! We're building Levh, a local-first memory layer for AI agents and workflows. It captures context from conversations, projects, files, email, calendars, and MCP tools, builds an inspectable knowledge graph, surfaces trust and conflict signals, and lets stale details fade over time all without cloud accounts or telemetry.

We're launching on Product Hunt soon and would love your early feedback, thoughts, or questions about the idea before we go live. Thanks for checking it out!

View all