Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Here's Codex talking to Fable 5 w/ my plugin. Unlike calling the API, `claude-channel-cli` talks to the same full Claude Code harness as you. This means you can talk to either AI & they'll guide each other naturally with shared memories, decisions, and research.

22,145 görüntüleme • 4 ay önce •via X (Twitter)

31 Yorum

Aaron Ng profil fotoğrafı
Aaron Ng4 ay önce

Grab the tool and the plugin at + Allows agents to talk to the same Claude Code harness as you, keeping context & memory. + Supports multiple sessions, pinned to project directories. + Works with any AI agent that can call a CLI, not just Codex.

TigerHix profil fotoğrafı
TigerHix4 ay önce

niiiiice

Diego | AI 🚀 - e/acc profil fotoğrafı
Diego | AI 🚀 - e/acc4 ay önce

Fable

Ethereal profil fotoğrafı
Ethereal4 ay önce

Gonna look into this for Cool stuff !

Josh Schuler profil fotoğrafı
Josh Schuler4 ay önce

Man this is so cool!

RoboRubin profil fotoğrafı
RoboRubin4 ay önce

Very cool! I run a permanent tmux claude session as my obsidian vault manager With this i can basically make my agents talk directly to my second brain and get all the info they need without having to dive into the vault themselves

Oury Major Diallo profil fotoğrafı
Oury Major Diallo4 ay önce

I actually do it through computer use and the clipboard and it works great. Making a plugin is a plus though

Ty Udy profil fotoğrafı
Ty Udy4 ay önce

This is dope bro

Rich Smith profil fotoğrafı
Rich Smith4 ay önce

Awesome! Can’t wait to try it! 😁 What was the video editing took you used?

Aaron Ng profil fotoğrafı
Aaron Ng4 ay önce

davinci resolve

AI Mastery Guide profil fotoğrafı
AI Mastery Guide4 ay önce

Two AI coding agents sharing memory and context in real time is actually a big deal. How stable is this in practice?

shortcutguy profil fotoğrafı
shortcutguy4 ay önce

This is the way

The SI Maximalist profil fotoğrafı
The SI Maximalist4 ay önce

Two agents sharing one context window means zero token tax on the handoff. the future of AI isn't bigger models. it's zero-latency routing

Vito Botta profil fotoğrafı
Vito Botta4 ay önce

Agents talking to each other is useful only if they share state and decisions. Without that, it is just two chat windows taking turns.

J A Z I I profil fotoğrafı
J A Z I I4 ay önce

but where is fable now?

Dante profil fotoğrafı
Dante4 ay önce

I've been using my codex-debate-partner agent for months for debating, reviewing plans and code from Claude. I usually set a /goal for them to debate until they reach consensus, and then present the plan to me.

Jon Shumate profil fotoğrafı
Jon Shumate4 ay önce

Thanks dude, this looks great! I'll test it out.

Timur Yessenov profil fotoğrafı
Timur Yessenov4 ay önce

This is the part I’d test hard: shared memory is useful only if both agents can see why a decision was made. Otherwise Codex and Claude just synchronize confidence. I’d want a tiny decision log beside the handoff, not just shared context.

Rayan A Cader profil fotoğrafı
Rayan A Cader4 ay önce

two AIs guiding each other through a game with shared memory is honestly the most interesting thing I've seen this week, crazy where things are heading

Luis Calderon profil fotoğrafı
Luis Calderon4 ay önce

I have the same thing in Memroos.

maddada • ghostex.dev profil fotoğrafı
maddada • ghostex.dev4 ay önce

Looks great! Would you like to collaborate on this in my ADE app? I already have orchestration but I need to work on the skills to make it better. Please let me know 🙏🏻

Adel Bucetta profil fotoğrafı
Adel Bucetta4 ay önce

the honest answer is that this is just the beginning of multi-ai orchestration

Sam Sung profil fotoğrafı
Sam Sung4 ay önce

oh nice this is really cool - I've been going back and forth with Codex and Claude Code

Aaron Ng profil fotoğrafı
Aaron Ng4 ay önce

Yeah, I made this because of how much copying and pasting I was doing. They should just work together

Sam Sung profil fotoğrafı
Sam Sung4 ay önce

a friend of mine is testing out this: He says it's better than subagents. Feels more like running a team vs slaved agents. You can run separate sessions, and have a primary orchestrator agent call up agents as needed or kill after they’re done. Use any models you have access to. You can disconnect and let them run headless or watch them work.

Blum profil fotoğrafı
Blum4 ay önce

looks like a damn useful plugin

Max Ziebell profil fotoğrafı
Max Ziebell4 ay önce

You're still talking like Mythos/Fable is accessible.

Aaron Ng profil fotoğrafı
Aaron Ng4 ay önce

Unfortunately I recorded this on Friday

Max Ziebell profil fotoğrafı
Max Ziebell4 ay önce

🤞 Let's hope it comes back soon.… it was the 🐐.

Charlie · 云马AI · 免🪜稳连 Claude/GPT/Gemini API profil fotoğrafı
Charlie · 云马AI · 免🪜稳连 Claude/GPT/Gemini API3 ay önce

这个玩法确实有意思,比单纯调 API 更像在拉两个同事一起干活。说实话我觉得最妙的是上下文能互相接上,不用每次重新解释背景,模型之间还能顺着彼此的判断往下走。

Arthur Lee profil fotoğrafı
Arthur Lee4 ay önce

This is neat - why not just use tmux sessions?

Benzer Videolar