Hey everyone - we re tremendously grateful for our fantastic launch yesterday, ending at #1 for the day. Thank you all for your support!
I started Tonkotsu because I saw a huge opportunity for a complete rethink of AI coding not just incremental adjustments to established tools and workflows. Having managed teams of hundreds of engineers at Meta, Microsoft, and Atlassian, it s been fascinating to me to find that the role of the developer has shifted overnight: you're now the manager of a team of agents. We're building Tonkotsu to help you succeed in that new role.
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!
Tonkotsu
@tokengeek thanks for your support! We think there's so much potential in recentering developers as managers of agents - with clean delegation, no micromanagement, but clarity into what the agents are doing and final approval over commits. Would love to hear your feedback from your refactor.
Just curious - when you use CC with a bunch of agents, are you starting up a bunch of terminal windows in parallel?
@derekattonkotsu Hey Derek, thanks for the response.
When it comes to the agents, I build them out dependant on the project - but as an example:
Top Level: Orchestrator
Second Level: Backend, Frontend, Backoffice, Database
Third Level: API, Testing, Security, Documentation
The orchestrator has no write permissions, but does have access to certain MCPs and Skills. The other agents have permissions, MCPS and skills granted to them depending on their role in the flow. They always report back to the orchestrator who keeps everything in check.
I can run these in parallel if the orchestrators are working on separate parts of the system and are both writing back to the documentation to detail what they have performed, are about to perform and are currently doing.
I find that instruction sets have to be concise enough that we don't fill context, but detailed enough that they tell the agent exactly what to do - it's a balancing act, but a very fun one to figure out.
Most importantly, having very clear documentation is vital - with clear acceptance criteria throughout.
Tonkotsu
@tokengeek Super interesting - thanks for sharing your setup.
Agree with the point about calibrating the right level of detail in the instruction sets. What we've also found important is to focus attention on the parts of the instructions that represent the key, consequential design decisions. Those are the parts that are the most leveraged for me to spend time thinking about.
On MCPs and skills - curious what are your go-tos in your setup?
Great job @derekattonkotsu and @fmerian
exiting to test it! I like a new way of linear and confluence, I like this approach!
Tonkotsu
@fmerian @josemarin Thanks for your support! Happy to be mentioned in the same breath as Linear and Confluence. The last part of it is also built-in verification with Test Plans and diff reviews. Excited to have you try it - let us know what you think!
@fmerian @derekattonkotsu Yeah, installed and testing right now!
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.
Tonkotsu
@hagenson thanks a ton for your support, Frank! It means so much to us to hear you're getting such great results :)
Humans in the Loop
@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!
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?
Here for the food, not the AI agents 😂 Congrats on the launch!
Tonkotsu
@ant0ine_gt Thanks for your support! We do love our ramen :)
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!
Humans in the Loop
@mustassim Thanks for the support, Syed - Looking forward to your thoughts