Tonkotsu - Manage a team of coding agents from a doc
byβ’
Tonkotsu is a fresh approach: a clean, focused GUI that lets you manage a team of coding agents from a doc. FREE during our early access program.
Replies
Best
This is such a clever approach to managing AI coding agents! Having everything controlled from a simple doc feels much moreintuitive than juggling multiple terminal windows. The "Plan β Code β Verify" workflow looks really well thought out.
Quick question: Does it support multiple agents working on different parts of a project simultaneously?
@bow_8_vegetaΒ Yes, absolutely. A huge design goal for us with Tonkotsu is to enable parallel work: multi-tasking and even multi-projecting. This maps really well to a manager's role: they lead their team to work across many projects concurrently, and we think that's key to leveraging AI to its fullest as well.
Report
I'm getting great results with Tonkotsu. The workflow is very similar to managing a team of intermediate level coders, but turnaround times of minutes, not days and weeks. It does the donkey work and and frees me up to solve the hard problems. In 30 years as a programmer, team leader, development manager, consultant, no single tool has given me this big a jump in productivity.
Opinionated, primarily designed for professional engineers. You don't start from scratch here, you start from an existing repo. You don't play around with models, it defaults to Sonnet 4.5. You don't chat with agents, you manage them.
Tonkotsu provides a different approach to coding with agents, spec-driven, from prompt engineering to context engineering. Love this direction!
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!
Report
Hunter
@mustassimΒ Thanks for the support, Syed - Looking forward to your thoughts
the shift from a chaotic chat interface to a structured doc feels like the right evolution for managing complex tasks. does the doc automatically update as the agents finish tasks, or do I need to manually refresh the state?
Replies
This is such a clever approach to managing AI coding agents! Having everything controlled from a simple doc feels much moreintuitive than juggling multiple terminal windows. The "Plan β Code β Verify" workflow looks really well thought out.
Quick question: Does it support multiple agents working on different parts of a project simultaneously?
Congrats on the launch! π
Handle
@bow_8_vegetaΒ Yes, absolutely. A huge design goal for us with Tonkotsu is to enable parallel work: multi-tasking and even multi-projecting. This maps really well to a manager's role: they lead their team to work across many projects concurrently, and we think that's key to leveraging AI to its fullest as well.
I'm getting great results with Tonkotsu. The workflow is very similar to managing a team of intermediate level coders, but turnaround times of minutes, not days and weeks. It does the donkey work and and frees me up to solve the hard problems. In 30 years as a programmer, team leader, development manager, consultant, no single tool has given me this big a jump in productivity.
Handle
@hagensonΒ thanks a ton for your support, Frank! It means so much to us to hear you're getting such great results :)
@Product Hunt features AI coding assistants every day. @Tonkotsu is different.
Opinionated, primarily designed for professional engineers. You don't start from scratch here, you start from an existing repo. You don't play around with models, it defaults to Sonnet 4.5. You don't chat with agents, you manage them.
Tonkotsu provides a different approach to coding with agents, spec-driven, from prompt engineering to context engineering. Love this direction!
Keep up the great work, @derekattonkotsu and team!
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!
@mustassimΒ Thanks for the support, Syed - Looking forward to your thoughts
Oasi
the shift from a chaotic chat interface to a structured doc feels like the right evolution for managing complex tasks. does the doc automatically update as the agents finish tasks, or do I need to manually refresh the state?