Xuan Jiang

fun seeker

[Xuan Jiang @Xuan04263449]

@jajamooa @JiangChonghe @MIT Exciting stuffs

[Xuan Jiang @Xuan04263449]

Always exciting to see more

[Han Zheng @hanzheng_7]

more demos to come!

[Xuan Jiang @Xuan04263449]

@wenhaocha1 Congrats!

[Xuan Jiang @Xuan04263449]

Personalize your harness for your tasks and grow with it 😉

[Ao Qu @ao_qu18465]

Your agent can now grow new abilities, just by asking.

Reef now supports personalized harness evolution with /reefine: describe what you want your agent to do. Reef builds the change, checks it, and ships a new version.

Examples:
💬 "> /reefine add a /chat mode for faster responses"
🔊 "> /reefine tell me out loud when you're done"
⚡ "> /reefine add jev as a tool": 120 papers screened in 9 s

Works with any agent harness through a Reef adapter: Codex, Hermes, OpenCode, Pi and Terminus 2 today.

Try it here: https://t.co/yUfl1eoj6F

#agent #harness #rsi #llm

[Xuan Jiang @Xuan04263449]

Honestly can’t wait to integrate this into my daily workflow

[Xuan Jiang @Xuan04263449]

@Jayzou3773 我大哥必须支持

[Xuan Jiang @Xuan04263449]

Train your model with just API call😉

[Ao Qu @ao_qu18465]

🚀 Reef now supports training with the Tinker API!

Unlock continual learning with LoRA training by changing just one line in your config. Collect feedback, train, and publish versioned updates. No local GPU required.

Thanks to @Jayzou3773 for implementing this feature! 🙌

Check out our repo and contributions are always welcome! 👇
https://t.co/IOhoLExXmI

[Xuan Jiang @Xuan04263449]

@hanzheng_7 Best project I’ve ever contributed to

[Han Zheng @hanzheng_7]

Reef just hit 1k GitHub stars ⭐️ in 10 days since we open-sourced it!

Huge thanks to everyone building with and supporting Reef. Let’s goooo Reef!!!🔥

Github: https://t.co/khqHcnbypi

[Xuan Jiang @Xuan04263449]

@BobbyZhouZijian It’s really helping engineers’ daily work flow

[Zijian Zhou @BobbyZhouZijian]

1k stars in a week. Reef is cooking 🔥
Continual learning infra feels like the next big thing.

Check out repo at: https://t.co/UTgCRGsZ5W

[Xuan Jiang @Xuan04263449]

@AlanShao111 Well it depends

[Xuan Jiang @Xuan04263449]

@yhfchitanda This is the first time infra completes inference server learning, looking forward to it!

[Hanfei Yu @yhfchitanda]

Check how Reef serves your self-improving agents uninterruptedly while learning! https://t.co/7fpVuevR34

[Xuan Jiang @Xuan04263449]

If you didn’t try it yet. Time for it

[Han Zheng @hanzheng_7]

Reef is taking off! 🔥 Within 2 days since we open sourced it, Reef got ~300 GitHub ⭐️!

Reef is the first open-source infrastructure designed to evolve both model weights and the agent harness from live experience.

Reef already supports:
🧠Model evolution: SAO, TTT-Discover, OpenClaw-RL, with more recipes coming.
🛠️Harness evolution: SkillClaw, Meta-Harness, GEPA, with native integration for pi, OpenCode, Hermes Agent, and more harnesses coming.

Come and build Reef with us at https://t.co/IsAcJZFNQq !

[Xuan Jiang @Xuan04263449]

Isn’t it amazing your agent evolve all the time on your hardest tasks?

[Han Zheng @hanzheng_7]

🚀One of the biggest questions for AI agents is whether they can continue expanding their capabilities after deployment.

Deployment brings the experience needed to keep improving. As @ilyasut has argued, future intelligent systems should learn from deployment.

But this requires more than a new learning algorithm. It requires turning the serving stack itself into a learning layer: collecting live experience, turning it into updates, and safely bringing those updates back into serving.

That’s why we built Reef.

Reef is open-source infrastructure for continuously evolving agents at live deployment. To our knowledge, it is the first open-source infrastructure designed to evolve both model weights and the agent harness from deployment experience.

Not just weights, but also prompts, memory, skills, tools, and orchestration.

Reef already supports:
🧠Model evolution: SAO, TTT-Discover, OpenClaw-RL, with more recipes coming.
🛠️Harness evolution: SkillClaw, Meta-Harness, and a general harness-evolution engine built on Cordis, with native support for pi @pidotdev , OpenCode @opencode , and more harnesses coming.

With Reef, inference is no longer the end of the pipeline. It becomes part of a continual loop:
serve → learn → evolve → serve again.

Reef is fully open source. We would love you to try it, build on it, and tell us what is missing!
⭐ GitHub: https://t.co/IsAcJZFNQq.
💬 Discord: https://t.co/UcMW6CTbww.

#AgenticAI #llms

[Xuan Jiang @Xuan04263449]

The idea is simple, the effort we put in is huge, the outcome for agents is phenomenal!

[Han Zheng @hanzheng_7]

Over the past few months, we’ve been thinking a lot about what it would actually take to build agents that continuously improve from their own experience. Today, we’re open-sourcing our continual learning infra, Reef.

The idea is simple: instead of treating inference as the end of the pipeline, Reef turns live agent interactions into a continuous learning loop. It serves real applications, captures trajectories and feedback as structured experience, and lets different learning recipes use that experience to improve the system.

What evolves isn’t just the model. Reef is designed to evolve the whole agent — model weights and the harness — then evaluate, version, and safely deploy those updates back into serving.

Really excited to finally share Reef we’ve been building toward continual self-improvement!

Come and check it out: https://t.co/IsAcJZGlFY

And join the Discord group for more updates: https://t.co/UcMW6CTJm4

[Xuan Jiang @Xuan04263449]

@ao_qu18465 Having inferencing server learning at the same time is a dream coming into reality

[Ao Qu @ao_qu18465]

https://t.co/1T2jy03kth

[Xuan Jiang @Xuan04263449]

@elonmusk what