it's really cool to see devin launch a kanban view of agents
strongly believe this will be the future of agent interfaces
we are entering a world where planning tasks (linear, jira), working on code, testing, and version control need to be tighly integrated in a single developer workflow
@aoagents has been building along this direction since Feb, and we also let you choose your own agent harness (claude code / codex / opencode)
the next leap might not be the model or harness, but great products that let developers effectively plan, execute, and verify multiple tasks in a completely seamless way
the amount of effort this community puts into @aoagents is insane.
tldr: what open source community mean to @aoagents
-> not a single Discord session gets postponed or delayed.
-> every day, someone is working on something.
-> some remotely, some from the AO house in BLR.
1/n
3 months ago I wrote that the nature of all knowledge work had fundamentally changed.
The shift, in one line: research and execution moved to agents. Judgment and verification became the whole job.
A lot of people were skeptical, and for good reason. How can you understand the work if you weren't the one executing it?
Turns out agents are pretty good at explaining their work visually, through HTML pages and SVG diagrams. So the job changes. You understand the system, decide on the goals, and verify if they were actually achieved.
This also unlocks something big: the ability to parallelize work, paired with better planning that the agents drive themselves. Which brings up a real possibility. You start getting work done at the speed of your thought and judgment.
For the last 3 months I've been building the interfaces and the product for exactly this, optimizing every feedback loop across the SDLC.
It's community-driven and open source, with ⭐7.4K GitHub stars so far. Today, all of my work happens through @aoagents . It's been a multifold productivity unlock on top of Claude Code / Codex.
If you're curious to know what makes this possible, or just eager to use this open source project yourself, I'd love to chat.
I built an AI system that builds itself.
Not metaphorically. The AI agents literally rewrote their own orchestrator, tested it, reviewed their own code, fixed their own CI failures, and shipped it.
Introducing Agent Orchestrator. Open source. Link below.
hey @SantoshYadavDev would mainly just love for you to try @aoagents once.
it has 7,000+ stars and 990+ forks organically. we are basically an ide for agents, you can spawn diff agents and all that will come in a single dashboard per project for example codex, cluade, opencode, grok etc etc.
https://t.co/OgLlf1NUUj
CMUX solves the "where are my agents running?" problem.
The next problem is "how do I manage 20 agents across multiple repos?"
That's where orchestration starts becoming useful.
We've been using AO to coordinate Claude Code, Codex, OpenCode, and custom agents while keeping sessions, PRs, reviews, and CI feedback tied together.
Different layer of the stack, but they pair surprisingly well.
I built an AI system that builds itself.
Not metaphorically. The AI agents literally rewrote their own orchestrator, tested it, reviewed their own code, fixed their own CI failures, and shipped it.
Introducing Agent Orchestrator. Open source. Link below.