React for Agents: Astro Creator Brings Hooks to his Meta-Harness, Flue
- ID
- 14477
- Status
- summarized
- Published
- 15 Aug 2026, 11:46 PM
- Fetched
- 16 Aug 2026, 12:43 AM
- Provider
- Latent Space
- Category
- developer-ai
- Original URL
- https://www.latent.space/p/flue-2
- Source URL
- https://www.latent.space/feed
Summary
- Score
- 7.0
- Created
- 16 Aug 2026, 12:44 AM
- Tags
- Audience
- developersvibe_codersai-agent-users
What happened
Fred Schott, creator of the Astro web framework (acquired by Cloudflare in January), has released Flue 2, the first stable version of his JavaScript-based agent framework. Flue 2 introduces React-style 'Agent Hooks' authored in TypeScript, with 16 built-in hooks like useSkill(), useTool(), and useSubagent(), allowing agents to dynamically reconfigure their state, tools, and capabilities before every model call rather than being statically defined upfront.
Why it matters
If you're building AI agents in JavaScript/TypeScript, Flue 2's hook-based approach gives you a concrete pattern for agents that adapt mid-conversation—e.g., a support bot that attaches an account-management tool only after verifying a user. Schott explicitly calls file-based agent routing an antipattern, so anyone currently organizing agents as one-file-per-agent should reconsider that architecture.
Discussion angle
Compare Flue's React-hooks mental model for agents against Python-centric frameworks like LangGraph or CrewAI—does the 're-render on every turn' pattern actually map cleanly to LLM agent loops, or is the React analogy forced?