Auditable rule-based memory for LLM agents
Store facts with provenance, apply incremental stratified Datalog rules, track retractions, explain derived answers with proof trees, and expose memory through an MCP server.
From Github Awesome — GitHub Trending Today #47: 4DAnyone, microduck, boop, PRAXIST, acryl, pgterm, sepia, OpenInstinct at 14:01
Problem: Replaces opaque piles of embedding matches with queryable, auditable facts and explanations.
For: Teams building LLM agents that need inspectable and logically explainable memory.
Products from this video
4DAnyone ACRYL Anti-Mage ask Boop Breakscale Bun Claude Code Confetti Control Center create-photo-flipbook-ui Drizzle ORM effect-mq Epic Infographics Epic Infographics ESLint Experiential FFmpeg fire-your-seo-agency Fire Your SEO Agency Gemini Gmail Goldie Google Calendar headcount Highball iMessage Jot Lemmalog LM Studio MemoraX Code Microduck Model Context Protocol (MCP) modelprint Ollama OpenAI Codex OpenInstinct Open Pstack Open Steps OpenTIE pgbot pgterm PostgreSQL Praxist Prettier Project SuperDex React Redis Refactoring UI (Claude Code skill) Rust sepia SnagTime SQLite Steam tare Tauri TSRX Vercel AI Gateway Vercel Blob Vite WebRTC whip Wine WolfCut
Examples
- lemmalog: provides provenance-aware memory, retractions, proof trees, and what-if queries to coding agents.