Introducing Flue — The First Agent Harness Framework
Flue is a TypeScript framework for building the next generation of agents, designed around a built-in agent harness.
Flue is like Claude Code, but 100% headless and programmable. There's no baked in assumption like requiring a human operator to function. No TUI. No GUI. Just TypeScript.
But using Flue feels like using Claude Code. The agents you build act autonomously to solve problems and complete tasks. They require very little code to run. Most of the "logic" lives in Markdown: skills and context and AGENTS.md.
Flue is like Astro or Next.js for agents (not surprising, given my background 🙃). It's not another AI SDK. It's a proper runtime-agnostic framework. Write once, build, and deploy your agents anywhere (Node.js, Cloudflare, GitHub Actions, GitLab CI/CD, etc).
We originally built Flue to power AI workflows inside of the Astro GitHub repo. But then @_bgiori got his hands on it, and we realized that every agent needs a framework like Flue, not just us.
Check it out! It's early, but I'm curious to hear what people think. Are agents ready for their library -> framework moment?
The Astro team just open-sourced Flue, a framework turning Claude Code into a headless agent system. Virtual sandboxes replace real containers, making it drastically cheaper to scale AI agent fleets. Watch our video to see how it works.
hitting this interesting cross-roads with flue:
1) repo automation, workflows
2) hosted agents
as the framework matures, the differences between them are becoming more obvious and more frustrating to design around (and by extension, for users).
for example: in astro, it was a specific design goal that our repo automation and human maintainers would reuse 90% of the same content. Shared skills, tools, configuration, etc. etc.
running "flue run triage" in a GitHub Action should be as close to a core maintainer opening up claude code in the repo and asking "triage this issue: URL"
but if you're building and deploying a hosted agent, you want your skills and tools and subagents to live alongside the agent code, not the sandbox file-system.
splitting your agent logic across "this logic (agent code, tools) lives in the codebase" vs. "this logic (skills, roles) lives in the sandbox" is a maintenance nightmare.
i'm not sure what the answer is, but I see projects like Sandcastle by @mattpocockuk laser-focused on repo automation. I trust Matt to build something great here that will be hard for us to compete with. We are trying to do too much for too many people.
meanwhile, I'm now talking with so many devs building agents (not just oss devs with oss repos) and there is no one doing what flue is doing today. A part of me really just wants to explore and optimize for this, and build the best framework for agents.
idk, talking out loud a bit. will spend more time exploring this this week. curious if anyone who's tried flue (or considered it) has thoughts!
Huge win of support for @tannerlinsley and the entire Tanstack ecosystem.
Tanner is one of the few people I know who watches npm download charts even more closely than I do, so I know he's got to be feeling good about this rn.
Well deserved!
New @Lovable projects now ship on TanStack Start.
That means full-stack React with SSR/SSG/CSR per route, server functions colocated with components, deploy-anywhere architecture, and type safety that helps both humans and AI generate better apps.
1/2
https://t.co/Vb962C0h3P
can we finally put the AI "all tech decisions will be frozen in 2024" meme to bed?
IMO the exact opposite is true. If software can stand on its own merit (faster, more reliable, better designed, etc) it has never been easier to adopt, potentially at huge scale, very fast.
Huge win of support for @tannerlinsley and the entire Tanstack ecosystem.
Tanner is one of the few people I know who watches npm download charts even more closely than I do, so I know he's got to be feeling good about this rn.
Well deserved!