AskCodi orchestrates AI coding, two ways. Talk to Codi, an AI CTO in the Mac app that runs a team of agents and picks the right model for every job. Or call the same orchestration as an OpenAI-compatible API. Bring your own key.
Key features
š¤ BYOK: Claude Code, Codex CLI, and more
š§ An AI CTO that plans, delegates, and ships
šø Auto model routing, low cost by default
šļø Remembers your whole codebase
š OpenAI-compatible API for any LLM
š Analytics and cost controls
This is the 4th launch from AskCodi. View more
AskCodi
Launching today
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.
Free Options
Launch Team / Built With
MakersClaw
MakersClaw
Even if we clearly explain the full product vision and guidelines to Codi upfront, how do we ensure the AI agents it runs don't drift off course during execution, especially on longer, multi-step tasks? What mechanisms are in place to keep them aligned with the original intent throughout, not just at the start?
MakersClaw
@piyush_bhansali2Ā The system has been tested to build out complete applications from start and we have seen certain behaviours from agents that is preventing it from driftingĀ
Codi truly acts as a supervisor - reviewing not just the PRs but also the plan
Agents are escalating to human users when some request doesn't align with the vision or user experience
Daily briefings shows what is built and what is left at any given time. Purposefully built to always stay updated of what agent is working on and correct as fast as possible
Agents are problematic in that format but alignment is core of the product we have built.
MakersClaw
@ankita_singh27Ā We have a few things built in that improve output quality while reducing cost. Codi acts as both a supervisor and reviewer for the other agents, and it also routes each task to the most cost-effective model using our routing algorithm. The routing doesn't rely only on benchmark scores - it also considers recent model performance and task difficulty. So instead of defaulting to Fable or GPT-5.6 Sol for everything, it'll often choose models like GLM 5.2, Kimi K3, or MiniMax M3 when they're sufficient. Across our benchmark suite, we've seen roughly 50% lower inference costs with only about a 0.5% drop in task completion.
MakersClaw
Hey PH š 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.
Congrats on the launch guys š„³! Quick question though I'd usually want to run 2-3 branches on the same repo at once (say a feature, a bugfix, and a refactor in parallel). Does AskCodi isolate that at the branch/worktree level within a single project so they don't conflict, or is the parallelism mainly across separate projects?