Tonkotsu

Manage a team of coding agents from a doc

Software Engineering

Developer Tools

Artificial Intelligence

Managing a team of coding agents from a doc feels like the next evolution of AI dev workflows 🚀 Curious when delegating parallel tasks, how do you handle conflicting suggestions or overlapping context between agents? I’ve seen a couple patterns that help keep agent output consistent and reviewable if you want me to share. � Product Hunt

looks interesting quick question is my code stored on your servers or does everything run locally

curious about the security side does tonkotsu have access to my codebase or api keys

Congrats on the launch, Derek. Tonkotsu feels like a genuinely fresh take on AI-assisted development. I really like the positioning of the developer as a manager of agents rather than being buried in tools, configs, or constant micromanagement. The calm, decision-first workflow is a strong and much-needed contrast to the usual noisy IDE experience.

Also, the ramen noodle logo is a great touch; it’s memorable, playful, and immediately sets Tonkotsu apart in a sea of very “serious” dev tools. One opportunity I see is refining how that logo scales and adapts across product surfaces (app UI, docs, marketing). A slightly more flexible system, variations for dark/light modes, or simplified marks for small UI contexts, I would be happy to help strengthen brand consistency as Tonkotsu grows.

The idea of managing agents directly from a doc is a clever UX shift. How does Tonkotsu handle context window limits when a project spans across dozens of files? Would love to know if there's a specific 'manager' agent role to keep the sub-agents in sync

Love the name, already on my way to get some ramen 😆 Congrats on the launch!

Really like that you’ve framed the interface as “manage a team from a doc” instead of yet another chat or IDE sidebar; that mental model feels closer to how senior engineers already reason about work.

The big tension I keep seeing with agent tools is between hiding complexity so it feels magic vs exposing enough of the chain-of-thought that people can actually debug when things go sideways.

Your UI looks intentionally minimal, so I’m curious how you’re thinking about surfacing “just enough” of what the agents are doing under the hood without turning it into an observability dashboard.

Managing agents from a doc instead of CLI or IDE is an interesting surface choice. The human-as-editor flow (agents commit, you refine before PR) makes sense... curious if Tonkotsu has guardrails for scope creep when multiple agents run in parallel on the same codebase.

Well done on the launch — this is a genuinely interesting project, and the workflow aligns closely with how I approach agentic development myself. I also noticed the SOC 2 audit and the emphasis on keeping everything within the local development environment, which is reassuring.

One question I had relates to data handling during LLM processing: what information, if any, leaves the local machine, and which providers are involved? Are there guarantees that this data is not retained or used for future model training by the underlying LLM vendors?

This is an area I often struggle to fully square from an enterprise adoption perspective, though it feels much less problematic for personal or side projects.

TBH I love the name Tonkotsu! Reading docs is always easier than managing workflows!

This looks great. I've been using Claude Code with a small army of focused agents recently and have been really happy with the results - but having something like this where it can help manage them all is exciting.

I have an old project which is severely deprecated. Interested to see how this would handle a major refactor!

I love the clean GUI approach, but I wonder how much control we actually have over the 'team' through that doc. Is it mostly for giving high-level commands, or can we jump in and micro-manage the specific logic if an agent starts heading in the wrong direction?

Your UI centers on a single doc that plans, delegates, and reviews. How do you translate that doc into enforceable task boundaries (dependencies, ownership, conflict avoidance) so multiple agents can move in parallel without stepping on each other?

It is the first tool that treats AI like a team, not a trick. How do you keep things transparent when agents make decisions?

Great job @derekattonkotsu and @fmerian
exiting to test it! I like a new way of linear and confluence, I like this approach!

Congrats on the launch! I get the positioning of this being fundamentally for developers (I am not a dev lol) but keen to try it out and see what results I get!

Doc-as-control panel for coding agents feels right. I’m tired of juggling prompts in five places. How do you keep context clean with a few agents at once? I’ll try it after standup. Free early access helps. Also, the name makes me want ramen.

Am I upvoting because I am craving ramen. yes.

Is this super cool and looking a lot better than antigravity, yes.

Do I have to bring my own API keys? Do you manage that? How is usage billed?

What's the biggest project you have built with this?