What is Levh?
Levh is an open-source, local-first memory layer for AI agents and the people who work alongside them. It captures context from conversations, projects, files, email, calendars, and MCP tools, then builds an inspectable knowledge graph that links people, projects, organizations, and decisions into relationships you can read and audit. Rather than a black-box score, Levh surfaces deterministic trust and conflict signals so you can see why a piece of context is considered reliable, and it lets stale details fade over time while important guidance stays pinned. Everything runs on your own machine: it stores data in SQLite with local embeddings and a deterministic fallback, and needs no cloud account, no managed database, and no Redis. Levh is MCP-native, exposing 59 tools that cover capture, recall, graph navigation, trust assessment, review, and decision support, and it also ships a dashboard, a REST API, and a WebSocket interface alongside the MCP server. The workflow is capture, understand, then recall: context comes in through MCP, CLI, API, or connectors; Levh analyzes trust, entities, conflicts, and decay; and it resurfaces the right context when an agent or person needs it. It installs with pip install levh and is released under AGPL-3.0. Levh suits developers and teams who want persistent agent memory they can inspect and keep on their own hardware, instead of a hosted memory service.
What is Levh used for?
Best for developers and teams who want persistent, inspectable AI agent memory that runs locally with no cloud account.
How much does Levh cost?
Pros and cons
Pros
- Local-first: stores data in SQLite with local embeddings, so no cloud account or managed database is required
- Inspectable knowledge graph links people, projects, organizations, and decisions into auditable relationships
- Deterministic, explainable trust and conflict signals instead of an opaque reliability score
- MCP-native with 59 tools, plus a dashboard, REST API, and WebSocket interface
- Memory decay lets stale details fade while important guidance stays pinned
Cons
- AGPL-3.0 license can be restrictive for some commercial or proprietary use
- Self-hosted and local-first, so you manage installation, storage, and upkeep yourself
- Newer project with a small ecosystem compared to established memory platforms
- Python-first install (pip install levh) may not fit every stack out of the box
Questions about Levh
What is Levh?
Levh is an open-source, local-first memory layer for AI agents and humans. 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 on your own machine.
Is Levh free and open source?
Yes. Levh is free and open source under the AGPL-3.0-or-later license. It is self-hosted with no paid tiers listed, so you run it on your own hardware rather than paying for a hosted service.
Does Levh work with MCP?
Yes. Levh is MCP-native and exposes 59 tools spanning capture, recall, graph navigation, trust assessment, review, and decision support. Alongside the MCP server it also provides a dashboard, a REST API, and a WebSocket interface.
Does Levh require a cloud account or external database?
No. Levh is local-first and stores data in SQLite with local embeddings and a deterministic fallback. It needs no cloud account, no managed database, and no Redis, so your memory stays on your own machine.
How do you install Levh?
Levh is a Python package. You install it with pip install levh and can then run levh doctor to check your setup. Context can be fed in through MCP, CLI, API, or connectors.
What are the best alternatives to Levh?
Mem0, Letta (MemGPT), Zep, OpenMemory, Cognee
Reviews
Sign in to rate and review Levh.
Sign in to reviewNo reviews yet. Be the first to review Levh!