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.
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, 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).
Design element Status ------ Runtime-parsed, stratified Datalog (interpreter, not proc-macro) ✅ Negation-as-absence with negative-cycle rejection ✅ Seminaive fixpoint with per-epoch delta maintenance ✅ Bi-temporal facts via validfrom/validto/assertedat columns + now() ✅ Semiring annotations: confidence (product t-norm) × provenance (set union) ✅ Annotation merge on re-derivation (max conf, union prov, deduped supports) ✅ why() proof trees with cycle protection ✅ Additive arithmetic in comparisons (D = Dm + 1) with linear solving ✅ Scoped negative deltas: retraction recomputes only transitive dependents ✅ ask() — read-only datalog query surface for agents ✅ Magic-sets demand evaluation (askdeep): point queries without full fixpoint ✅ Per-position secondary indexes; row-id lookups; WAM-st
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/JordyZomer--lemmalog.html)
Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, n
rokbenko/quackd🦆🧠 Give your Microduck a brain. Tell a small robot with two legs what you want in plain language. An LLM (Claude, OpenAI, Gemini, Grok) uses the skills it already has to do it. Includes a simulator, .
Evermemoai/evermemoA tiny, universal memory engine for humans and AI agents — CLI, HTTP API, MCP server, and shared memory hub in one small Go binary
replenhq/replenSmarter AI Development Workflows
sillogic/sill-ensoulLong-term memory for CLI agents — cross-CLI, cross-project, cross-session. OKF Wiki + MCP server, model-agnostic.
2672243194/agentbrainLocal-first long-term memory for AI agents - plain Markdown vault + thin MCP server. CJK-aware BM25, token-efficient by design.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.