Browse
→ AI & Models
→ Lemmalog
Lemmalog
Datalog-based memory and reasoning engine for LLM agents, with a Rust engine, REPL, skill package, and MCP server exposing 12 stdio JSON-RPC tools. It models agent memory as provenance-tracked facts and stratified rules for temporal queries, contradiction candidates, relevance diffusion, and incremental derived views. Public GitHub repository created August 27, 2026.
MCP unverified
Integration
| Transport | stdio |
| Auth | none |
| Endpoint | lemmalog-mcp |
| Install | git clone https://github.com/JordyZomer/lemmalog.git && cd lemmalog && cargo build --release --features mcp |
Use Cases
| 01 | Give MCP-compatible agents a shared deductive memory instead of relying only on vector retrieval |
| 02 | Query current and historical facts with provenance back to source episodes |
| 03 | Install versioned rule batches and update derived memory views incrementally across sessions |
Tags
agent-memory datalog provenance deductive-database temporal-reasoning rust claude-code kimi
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>