What does lemmalog do?

It provides a Datalog-backed memory engine with an MCP server interface for LLM agents.

Is lemmalog an official MCP server?

No. It is tracked as a community server from the public GitHub repository.

How do I install lemmalog?

Use the GitHub repository as the source of truth and follow its current README installation instructions.

lemmalog

Name: lemmalog
Author: JordyZomer

by JordyZomer

communitystdiogithub

View all implementations

252stars|18forks

View on GitHub Docs

Works withClaude DesktopCursorVS CodeWindsurf

Screenshots

About

Datalog-backed memory and reasoning context for LLM agents through an MCP server.

Features

Datalog rule engine for agent memory
Provenance-tracked facts for inspectable context
Incremental derivation for updating memory state
MCP server interface for agent harness integration

Use Cases

Agent framework builders

Give agents a shared reasoning memory that can store facts and derive new context.

AI infrastructure teams

Experiment with Datalog as a structured memory layer instead of unstructured notes.

What This Server Can Do

MCP servers expose three types of capabilities to AI clients. Here's what lemmalog supports.

Tools

Supported3 tools

Functions your AI client can call to perform actions — like querying a database, creating a file, or calling an API.

How to use: Tools run automatically when your AI client decides they're needed. Ask your AI assistant to perform a task, and it will invoke the right tool.

Resources

Supported

Read-only data sources this server exposes — like files, database schemas, or API responses your AI client can read for context.

How to use: Resources are loaded as context when your AI client needs background information. Ask about the data this server manages, and resources get pulled in automatically.

Prompts

Not available

This server does not provide pre-built prompt templates.

For the full list of available tools, resources, and prompts, check the README on GitHub.

Available Tools (3)

query_memory

Query derived or stored facts in the Datalog memory engine.

assert_fact

Add a provenance-tracked fact to the memory store.

derive_context

Run rules to derive context for an agent task.

Frequently Asked Questions

OpenAIai lab

Creating safe AGI that benefits all of humanity

249 Tools58 MCP Servers14 ModelsFounded 2015San Francisco, CA

View full profile

249 Tools·14 Models·58 MCP Servers·5.0avg

Tools by OpenAI

Other AI tools from the same organization.

AgentGPT

Automation

AgentGPT: Pricing, Features, FAQs, and Alternatives

ChartGPT

Chart Generator

A Comprehensive Tool for All Your Charting Needs

GPT Stylist

Figma Plugin

Create custom color palettes effortlessly with GPT Stylist

GPT Lab

Collaboration

Transform data scripts into interactive web apps in minutes with Streamlit.

AutoGPT (Hugging Face)

Automation

Automate Your Tasks with AutoGPT by aliabid94

SiteGPT

AI Assistant

Personalized AI Chatbot for Enhanced Customer Support

View all tools

AI Models by OpenAI

AI models from the same organization.

Model	Context Window	Price (In / Out per M)	Capabilities
GPT-6.1 SolCurrent	1.1M	$2.00 / $10.00	textvisionreasoningcoding+4
GPT-6 SolCurrent	1.1M	$2.00 / $10.00	textvisionreasoningcoding+3
GPT-6 LunaCurrent	1.1M	$0.10 / $0.50	textvisionreasoningcoding+3
GPT-5.6 LunaCurrent	1.1M	$0.20 / $1.20	textvisionreasoningcoding+5
GPT-5.6 TerraCurrent	1.1M	$2.00 / $12.00	textvisionreasoningcoding+5
GPT-5.6 SolCurrent	1.1M	$4.00 / $20.00	textvisionreasoningcoding+5