1,000 stars less than 2 weeks after public announcement ✅ @AndreyAvtomonov vibe coded star counter followed us everywhere on launch day Ask Claude Code/Codex to run this: Run npx skills add Kaelio/ktx --skill ktx and use ktx skill to install and configure ktx Or head over to the repo: github.com/Kaelio/ktx

Claude Fable 5 is out - here's how it does on direct access to postgres dbt versus via ktx. Automated context ingestion and maintenance is valuable in so many ways: - Accuracy - Speed - Token consumption As a side note, @AnthropicAI did mention that they will require 30-day retention for all traffic on Mythos-class models. The data won't be used to train new Claude models, or for any non-safety-related purpose. But you probably should be aware since it's buried at the bottom of the release announcement

The data team at @AnthropicAI just published its internal playbook for self-serve analytics. We reverse-engineered it and open-sourced the result. Here's how to set it up at your company: kaelio.com/blog/open-source-… Our post walks through each component of Anthropic’s internal agentic analytics system and explains how we packaged the same 4 layers as 1 installable engine that builds and maintains itself, with a human-in-the-loop mechanism. Repo: github.com/Kaelio/ktx

Context is king, especially in the age of AI, where everyone is connecting their agents to their data stack. But writing SQL was never the hard part. Making it accurate and trustworthy against your warehouse has always been.

ktx is an open-source context layer that automatically builds and maintains the semantic and business knowledge agents need to query your warehouse accurately. - Ingests wiki content, removes duplicates, and flags contradictions for human review - Detects joinable columns and resolves chasm and fan traps automatically - Combines full-text and semantic search across wiki and semantic-layer entities - Ships CLI and MCP tools for agent execution

AI data agents hallucinate SQL because they have no idea what your metrics actually mean. ktx (@KaelioAI) auto-builds a context layer from your warehouse, dbt, and query history so agents query accurately. Open-source, runs local. What's in the context layer? Next tweet. #DevTools

Today we’re open-sourcing ktx: the context layer for data agents. ktx is the alternative to traditional semantic layers and wiki-style knowledge bases. Repo: github.com/Kaelio/ktx