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
🤖 BYOK: Claude Code, Codex CLI, and more
🧠 An AI CTO that plans, delegates, and ships
💸 Auto model routing, low cost by default
🗂️ Remembers your whole codebase
🔌 OpenAI-compatible API for any LLM
📊 Analytics and cost controls
This is the 4th launch from AskCodi. View more
AskCodi
Launched this week
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
Congrats on launching a neat product! QQ: the cost story depends on Codi correctly calling a task 'boring' and handing it to a cheap model, and the tasks that look boring but aren't are exactly where cheap models produce plausible-wrong output. How are solving this conundrum if I didn't invent it at all and it exists?
AskCodi
@artstavenka1 Not boring but suitable. Our algorithm uses public data to see which models perform well for which task. It is about reaping the cost benefit without loosing the accuracy too much. Plus the systems in place (skills and supervisor) boost the accuracy instead of dropping it. It is not a pure llm router, llm just classifies the task as to what kind of task it is and then we choose the best cheapest model for it. Hope that cleared it up a bit.
MakersClaw
@artstavenka1 To add to Shreyans’ answer: routing isn’t a one-way decision. The engineer’s output still has to satisfy the task’s acceptance criteria, tests, and review. If the result exposes unexpected complexity or fails validation, Codi can treat that as evidence that the task was misclassified and escalate it to a more capable model. The savings come from starting efficiently, not from being committed to the first model choice.
@shreyans_assistiv Congratulations for your launch. Does Codi work across multiple projects simultaneously, or is it limited to one repo at a time like other AI coding tools? The description mentions "parallel across all your projects", just wanting to confirm if that means true multi-project orchestration from a single inbox.
MakersClaw
@shreyans_assistiv @jayant_surana1 Yes, it is true multi-project orchestration. You can run multiple Codi sessions across different projects simultaneously, while approvals and questions from every session arrive in one inbox. You do not need a separate terminal or agent manager for each repo.
AskCodi
@jayant_surana1 It is truly multi project. Codi has a /standup mode where it can starts sessions across multiple projects based on need and token usage left.
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_bhansali2 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 drifting
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.
Congrats on the launch guys 🥳! 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?
MakersClaw
@raunak_bhansali Thanks! 🙌 Great question. Isolation is at the worktree level: each task gets its own branch and git worktree, so a feature, a bug fix, and a refactor never share a working tree or step on each other. Right now Codi runs them isolated and coordinates them rather than firing all three at the exact same instant, and true simultaneous same-repo branches are on the near-term list. Across projects it's already fully parallel.
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.
I have a small question for the dev team:
What kind of tasks has it been best at for you so far? Trying to figure out where it'd fit in my workflow.
AskCodi
@nolan_vu if you are working across multiple projects, understanding each projects needs and prioritising your token usage is best application we have seen. Coding is good but it outshines on orchestrating.
@shreyans_assistiv I see. So have you guys done good with managing the tokens efficient to optimize the operation at first
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