Загрузка видео...

Не удалось загрузить видео

На главную

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 просмотров • 4 месяцев назад •via X (Twitter)

Комментарии: 31

Фото профиля Aaron Ng
Aaron Ng4 месяцев назад

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.

Фото профиля TigerHix
TigerHix4 месяцев назад

niiiiice

Фото профиля Diego | AI 🚀 - e/acc
Diego | AI 🚀 - e/acc4 месяцев назад

Fable

Фото профиля Ethereal
Ethereal4 месяцев назад

Gonna look into this for Cool stuff !

Фото профиля Josh Schuler
Josh Schuler4 месяцев назад

Man this is so cool!

Фото профиля RoboRubin
RoboRubin4 месяцев назад

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

Фото профиля Oury Major Diallo
Oury Major Diallo4 месяцев назад

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

Фото профиля Ty Udy
Ty Udy4 месяцев назад

This is dope bro

Фото профиля Rich Smith
Rich Smith4 месяцев назад

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

Фото профиля Aaron Ng
Aaron Ng4 месяцев назад

davinci resolve

Фото профиля AI Mastery Guide
AI Mastery Guide4 месяцев назад

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

Фото профиля shortcutguy
shortcutguy4 месяцев назад

This is the way

Фото профиля The SI Maximalist
The SI Maximalist4 месяцев назад

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

Фото профиля Vito Botta
Vito Botta4 месяцев назад

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

Фото профиля J A Z I I
J A Z I I4 месяцев назад

but where is fable now?

Фото профиля Dante
Dante4 месяцев назад

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.

Фото профиля Jon Shumate
Jon Shumate4 месяцев назад

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

Фото профиля Timur Yessenov
Timur Yessenov4 месяцев назад

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.

Фото профиля Rayan A Cader
Rayan A Cader4 месяцев назад

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

Фото профиля Luis Calderon
Luis Calderon4 месяцев назад

I have the same thing in Memroos.

Фото профиля maddada • ghostex.dev
maddada • ghostex.dev4 месяцев назад

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 🙏🏻

Фото профиля Adel Bucetta
Adel Bucetta4 месяцев назад

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

Фото профиля Sam Sung
Sam Sung4 месяцев назад

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

Фото профиля Aaron Ng
Aaron Ng4 месяцев назад

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

Фото профиля Sam Sung
Sam Sung4 месяцев назад

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.

Фото профиля Blum
Blum4 месяцев назад

looks like a damn useful plugin

Фото профиля Max Ziebell
Max Ziebell4 месяцев назад

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

Фото профиля Aaron Ng
Aaron Ng4 месяцев назад

Unfortunately I recorded this on Friday

Фото профиля Max Ziebell
Max Ziebell4 месяцев назад

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

Фото профиля Charlie · 云马AI · 免🪜稳连 Claude/GPT/Gemini API
Charlie · 云马AI · 免🪜稳连 Claude/GPT/Gemini API3 месяцев назад

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。

Фото профиля Arthur Lee
Arthur Lee4 месяцев назад

This is neat - why not just use tmux sessions?

Похожие видео