AIRust★ 213
JordyZomer/lemmalog
LEMMALOG: DATALOG FOR AGENT MEMORY
Lemmalog — a Datalog engine for LLM agent memory. It supports stratified rules, provenance‑tracked facts, incremental derivation, and an MCP server that lets you use the engine as a shared brain.
// KEY FEATURES
- Stratified Datalog rules guarantee correct logical inference without cycles.
- Facts are stored with provenance metadata, letting you trace each derivation's source.
- Incremental updates recompute only the rules affected by fact changes.
- The MCP server exposes the engine via API, turning it into a shared brain for agents.
#agent-memory#datalog#knowledge-graph#llm#llm-agents#mcp#neurosymbolic
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram