Flue 2.0: Agent Framework Adopts Hooks Architecture

ArticleFred K. SchottAnnouncement

Flue 2.0 rebuilds the TypeScript agent framework around a React-inspired hooks API. This allows developers to build dynamic agents that can adapt models, tools, and persistent state at runtime as conversations evolve.

Key points

  1. Agent Hooks: 16 built-in hooks (such as useModel, useTool, and usePersistentState) replace static upfront configuration with dynamic state management.
  2. Dynamic Capabilities: Agents can conditionally upgrade models or attach specialised tools based on workflow steps or verification status.
  3. Vite and Hono Foundation: The custom CLI build pipeline is replaced by standard Vite plugins and Hono route handlers, supporting Cloudflare Workers and Node.js.
  4. Stateless MCP Support: Remote Model Context Protocol tools can be mounted dynamically and optionally using useMcpConnection.
  5. Conversation-Scoped SDK: The new @flue/sdk and @flue/react libraries streamline tracking live updates, streaming chat into user interfaces, and managing task lifecycles.

Why it matters

Standard agent SDKs usually enforce static definitions at compile time, which makes multi-step triage and stateful transitions difficult to manage. Flue's hook-based composition brings a familiar declarative model to complex agent workflows.

Analysis

Fred K. Schott applies the compositional paradigm of React hooks to AI agents. Rather than defining rigid multi-agent systems, agents can evaluate their own persistent state on each run and alter capabilities on the fly. By handing routing and bundling over to Hono and Vite, the framework reduces surface area and leans into modern web infrastructure.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • X post:fks

    Flue 2: TypeScript Agent Framework Adopts React-Inspired Hooks

    Fred K. Schott has announced Flue 2, a TypeScript framework for building AI agents that introduces a React-style hooks pattern to tackle capability composition and runtime adaptability.

    639bookmarks126.6kviews

    AI & LLMs· Announcement

  • Link:DeepSeek

    DeepSeek Harness: Modular Open-Source Framework for AI Agents

    DeepSeek has launched a developer preview of DeepSeek Harness, an open-source runtime framework for AI agents. Built on the Cordis kernel, it implements an architecture where all capabilities are plugins alongside an append-only event stream for full traceability.

    AI & LLMs· Announcement

  • Repository:deepseek-ai/deepseek-harness

    DeepSeek Harness: Plugin-Based Open-Source AI Agent Framework

    DeepSeek Harness (dsh) is an open-source AI agent harness by DeepSeek AI. Built with TypeScript and Cordis, it uses an 'everything-is-a-plugin' architecture to provide modular agent capabilities and a Web UI.

    212.8kstarsTypeScript

    AI & LLMs· Tool

  • Repository:langchain-ai/langchain

    LangChain: Open-Source Agent Engineering Platform and LLM Framework

    LangChain is an open-source framework designed for building agents and LLM-powered applications in Python and JavaScript/TypeScript. It provides modular building blocks, third-party integrations, and specialized tools like LangGraph and Deep Agents.

    145.7kstarsPython

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.