Announcements, research, engineering and product updates on the Compiled Knowledge Format.
A comparative analysis between CKF and the main global alternatives for structuring documents, preparing data for LLMs, building RAG, creating knowledge graphs, and standardizing APIs.
The same idea — Compiled Knowledge Format — explained five times, each level zooming in: a 10-year-old, a teenager, a non-technical adult, a technical professional, and an Information Retrieval specialist.
A scientific retrospective of the CKF Compiler, tracing the journey from CKF-0.1 (≈10% semantic preservation) to v1.03.1 — the first balanced release that simultaneously preserves meaning, structure, retrieval surface, sanitation, metadata and traceability.
A vision paper proposing CKF — an open format that compiles documents into typed, schema-stable knowledge packages — and KnowOps, a framework that ports software-engineering lifecycle practices to agent-consumed knowledge bases. Empirical efficacy is the subject of a pre-registered confirmatory study currently in preparation.
Karpathy formulated one of the most important architectural intuitions of the current AI phase: raw documents should be compiled into persistent artifacts before being queried repeatedly by LLMs. CKF extends that intuition to the case where the consumer of the compiled artifact is not a human, but an agent.
A strategic analysis of CKF as a semantic IR — beyond RAG and GraphRAG, alongside RDF/OWL and MCP, with provenance and validation as foundational primitives.
A walk through fourteen foundational papers — from Attention Is All You Need to DSPy and the LLM Wiki — and the case for CKF as a proposed layer of compiled knowledge.
An open format for compiling human documents into structured, agent-ready knowledge packages.
An argument for why documents designed for human readers are a poor fit for machine readers, and what a machine-native format might look like.
RAG falha de quatro formas: paramétrica, de retrieval, contextual e composicional. Este artigo nomeia e descreve o quarto tipo — Composition Hallucination — mostra por que aumentar chunks ou contexto não resolve, e propõe diagnóstico e implicações para quem constrói RAG, GraphRAG e agentes.