lemmalog MCP Server
JordyZomer/lemmalog
[](https://agentrank-ai.com/tool/JordyZomer--lemmalog/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) A Datalog engine for LLM agent memory: stratified rules, provenance-tracked facts, incremental derivation, and an MCP server that lets your harness use it as a shared brain.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
JordyZomer/lemmalog is a Rust MCP server licensed under MIT. A Datalog engine for LLM agent memory: stratified rules, provenance-tracked facts, incremental derivation, and an MCP server that lets your harness use it as a shared brain. Topics: agent-memory, datalog, knowledge-graph, llm, llm-agents, mcp, neurosymbolic.
Ranked #720 out of 24842 indexed tools.
In the top 3% of all indexed tools.
Ecosystem
Score Breakdown
330 stars → growing community
Last commit 10d ago → recently updated
5/6 issues closed → responsive maintainer
5 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Badge all embed codes →
[](https://agentrank-ai.com/tool/JordyZomer--lemmalog/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/JordyZomer--lemmalog/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/JordyZomer--lemmalog" alt="AgentRank"></a> Matched Queries
From the README
# Lemmalog A Datalog engine for LLM agent memory. This repo contains the engine (Rust crate, MCP server, REPL, agent skill) plus the design document ([`datalog-context-engine-design.md`](datalog-context-engine-design.md), with an honest status log of what shipped). The thesis: **an agent's memory should be a deductive database** — the agent builds a *verifiable model of what it knows* and mechanically reasons over how that knowledge changes, rather than "remembering better" than a vector store. Base facts are asserted at the ingestion boundary (LLM extraction); rules derive closures, temporal projections, contradiction candidates, and relevance diffusion; every fact carries provenance back to its source episodes; and each conversation turn updates derived views incrementally instead of re-deriving them (or worse, re-reasoning them in-context). ## What's implemented | Design element | Status | |---|---| | Runtime-parsed, stratified Datalog (interpreter, not proc-macro) | ✅ | | NegatRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.