Radar / AI infrastructure / Blume 2.0
Blume 2.0: open-source docs framework for humans and agents
Blume 2.0 launched on Product Hunt on Oct 4: an MIT-licensed, zero-config docs framework that turns a Markdown folder into a production docs site with built-in llms.txt, MCP server, and an agent-readability scorer.
Why it matters
Docs built for the agent era: every page ships raw Markdown, llms.txt, and a hosted MCP server, and 2.0 adds an agent-readability score so teams can audit docs the way they audit SEO.
What you could build with it
A developer-tools startup could ship its API docs on Blume and expose the built-in MCP server and llms.txt to customers' coding agents, so users get accurate answers grounded in current docs instead of stale web results.
Does it hold up?
Too early to judge: 2.0 went live on Oct 4 and the only evidence so far is launch-day discussion on Product Hunt.
Built with Blume 2.0
- Blume agent skill in fluidity-tailwindgithub · Community-maintained SKILL.md (in a Tailwind plugin repo) that teaches coding agents how to scaffold, configure, and customize Blume docs sites.
- omicrxn/mercury: docs site migrated from SvelteKit to Blumegithub · Real migration commit moving an SvelteKit + Velite + mdsx docs app to Blume (166 files changed), replacing hand-written llms-full.txt with Blume-generated search, llms.txt, and OG images.
- Meet Blume: An Open-Source, Zero-Config Documentation Frameworkmarktechpost · Independent writeup of Blume's 1.0 launch covering its zero-config Markdown model, Astro/Vite stack, built-in llms.txt/MCP, and MIT licensing.
- dnunez24/fluidity-tailwindgithub · Bundles a community Blume SKILL.md that lets coding agents scaffold and configure Blume docs sites.
Learn more
official docs FAQ (technical deep dive) →
First spotted on article: source.
More AI infrastructure
Modular open-sources MAX inference server, Mojo stdlib and accelerator kernelsThe core of Modular's unified AI deployment stack is now open: the MAX inference server (OpenAI-compatible endpoints)…infra · JEV 0.76OmniRouteFree MIT AI gateway: one endpoint, 290+ providers and 500+ models with quota-aware auto-fallback.infra · JEV 0.75Context Mode: context-window optimization for AI coding agentsMCP server for AI coding agents that sandboxes verbose tool output and persists session memory, cutting context use by…infra · JEV 0.74StrataOpen-source inference engine that runs the 125B-parameter Qwen3.8-Flash-Next MoE on a single consumer GPU with 12GB+…infra · JEV 0.74Microsoft releases 301,000 Copilot coding-agent tracesMicrosoft open-sourced 301,026 GitHub Copilot coding-agent sessions (9.3M model calls, 8.7M tool calls) with timings…infra · JEV 0.71claude-memCaptures tool-use observations across agent sessions, compresses them with AI into SQLite + Chroma hybrid search, and…infra · JEV 0.7
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.