AskCodi - Orchestrate agents at scale while reducing cost
by•
Tell Codi what you want to build. It writes the plan, runs AI agents in parallel across all your projects, and picks the cheapest model that can do each task, so you ship more and spend less. When you add a project it writes the charter and task list itself, and only pulls you in when a decision needs you, through one inbox.
Replies
Holy Sh*t! I love this! Is this currently limited to Claude or can I use any LLM?
AskCodi
@sm0r3ll It works with claude code, openai codex and rest of the models on the market are served through askcodi gateway at provider api prices. BTW loved your reaction :D
@shreyans_assistiv I tried new version, What happens if I update the feature board while the agent is running on the task?
AskCodi
@ankita_singh27Â Codi adapts, checks if any task are dependent on the change and updates them accordingly. It acts as a true supervisor.
PRISM by Block Convey
This is a great product, I was skeptical at first. I use co-work right now, but this really work done
AskCodi
@arun_prasad06Â Thank you for giving us a chance. Most of the tools are designed for the 200 USD plan, we are aiming to optimise for a market where everyone doesn't have 200 dollars every month to spend on AI
Swytchcode
Thats a nice concept. How do you handle cases where you may need to use multiple models?
AskCodi
@chilarai Codi when sets up Agents for a task, thats where our auto routing comes into play so always the best model for that task. I hope I am understanding your question correctly. What case do you see for needs multiple models. Would love to understand, thank you
The Mac app plus API combo is interesting. Is AskCodi meant mainly for individual developers working locally on their own machine, or for teams that want to build AI workflow automation into existing engineering processes? The topic mix includes Productivity, AI Agents, and Vibe Coding Tools, so I’m curious where you see the primary use case landing first.
AskCodi
@ivory_xuxuxu It is currently for individual users but it is designed to be collaborative. The whole setup is designed to accelerate work not just between multiple agents but build an environment where each member on the team can each run multiple agents and still run without clashing.
AskCodi
@joviechen It works on top of your claude or openai subscription + you have access to all the other models via the askcodi gateway at provider api cost.
MakersClaw
Hey PH 👋 Sachin here, One more thing for anyone coming over from Product Hunt today.
The app is free to try for 7 days, no strings. After that it's $60 for the year. Most people spend more than that on AI in a couple of months, and Codi is built to send the cheap work to cheap models, so it usually saves you more than it costs.
Two ways you'd genuinely help us:
1. Tell us the first moment Codi lost your trust. That's the thing we most want to fix.
2. If you juggle more than one project, tell us whether having Codi run them in parallel actually saves you time.
We're around all day and will answer every comment. If something breaks, reply here or reach out to us via the web app support and we'll jump on it.
Scarlett.
How does Codi decide which model to route a task to?
Is that automatic or do I configure it?
AskCodi
@byalexai So all you need to configure are the providers - anthropic models through claude code, openai models through openai codex and rest of the models on the market through askcodi gateway.
Model selection is auto by codi based on the best model to complete the task with as much saving as possible. Routing is always of today's performance of the model. So on the day of launch Sonnet 5 would definitely be better than Opus 4.8.
MakersClaw
@byalexai To add one detail: your provider setup defines the pool Codi can choose from. Within that pool, Codi looks at the task type, required capabilities, cost, and current model performance. The selected model still has to satisfy the task’s acceptance criteria and review checks, so routing is not based on price alone. If a task turns out to be more complex than expected, Codi can move it to a stronger model.
Pluno
Interesting - how did you build the model routing?
AskCodi
@korbinian_abstreiter It is a combination of LLM Routing + benchmarks + public dataset of model performance over time. We keep experimenting and this adaptive routing is currently showing the best performance.
the auto model routing to the cheapest capable model is the part I'd want to see fail-safes on - if the cheap model starts producing worse output mid-task does Codi notice and escalate, or does that only get caught when you review the final diff?
AskCodi
@sabber_ahamed Definitely, it is tricky to design failsafes mid task. So how we have do it is each agent works with the task in breakpoints with Codi supervising along the implementation. Plan and PRs are already reviewed by Codi.
@shreyans_assistiv breakpoints as the checkpoint unit is a clean answer - keeps a human-reviewable diff at every stage instead of trusting one giant autonomous run.
AskCodi
@sabber_ahamed it has to be the basis of any autonomous long running agentic system