OpenKB: open-source LLM knowledge base hits 4.9k stars with vectorless reasoning-based retrieval
tom_doerr · x · 2026-11-13
OpenKB (VectifyAI, 4.9k GitHub stars, Apache-2.0) compiles raw documents into a structured, interlinked wiki-style knowledge base using LLMs, based on an idea by Andrej Karpathy: auto-generated summaries, concept pages and cross-references that compound over time instead of being re-derived per query.
- No vector DB: uses PageIndex's vectorless, reasoning-based retrieval, suited to long documents
- Recent updates: Google Open Knowledge Format (OKF) support; auto-extracted entity pages (people, orgs, places, products) kept in sync
- Ships as a CLI with a Claude plugin, skills, and native multi-modality
Unlike traditional RAG, which rediscovers knowledge from scratch on every query, OpenKB compiles knowledge once into a persistent wiki and keeps it maintained.
More from coding & agent
- Google launches Gemini 4 Hydrogen: $1.5/$7.5 per M tokens, 1M context, Orchestrator in Antigravity — testingcatalog · 2026-11-13
- vork: open-source headless 3D/VFX engine for AI agents, renders black hole bending light in 18 min — ravisparikh · 2026-11-13
- Agent swarm spends $3M/month in tokens to build game Spawn, treats an hour without shipping as SEV-0 — dl_weekly · 2026-11-13
- Replit Agent can now buy supplies via Link and Visa and run Google Ads for your business — amasad · 2026-11-13
- 2-bit DeepSeek V4.1 Flash runs a coding-agent seat on two 2016 V100s: a 12-hour real-work trial — a4mula · 2026-11-13
- GitHub's practical guide to agent skills: build once, run on any agent — GitHub Blog AI/ML · 2026-11-13