Skip to content
CODOROby Osokoro
Product preview — macOS

Switch models mid-task. Know the bill before it arrives.

Codoro is a desktop IDE where the agent is a first-class part of the project. Route each task through a reviewable policy, cap what any run is allowed to spend, and choose a supported provider API key or dollar-valued Codoro credits across the live Vercel AI Gateway catalogue. Codoro does not claim or resell access from a separate provider subscription.

Free with your own API keys. Paid plans meter tokens, never features.

budget.tsrouter.tspage.tsx
1 // Reserve before the call, settle after. Never after only.
2 export async function reserve(run: Run, est: Cents) {
3 const cap = await capFor(run.scope);
4 if (run.spent + est > cap) {
5 return { ok: false, reason: "cap", cap };
6 }
7 // A cheaper model is offered, not substituted silently.
8 return { ok: true, hold: await hold(run.id, est) };
9 }
mainTS 5.9Ln 8, Col 42Claude Sonnet 5 · $0.41 / $2.00

Interactive product mock — Editor, Design, Plan and Chat can be explored above; this is not a downloadable build.

Four surfaces, one project

Four Codoro product surfaces

01 Editor

Agents that plan, edit, test and undo

Multi-file edits with a diff you approve, allowlisted build and test checks, and optimistic undo for the reviewed source changes.

02 Design

A canvas bound to the files

Manifest-declared frame previews bound to repository paths, tokens read from the stylesheet, and an edit that arrives as a diff rather than a handoff.

03 Plan

A project board beside the repository

Track milestones, owners and blockers in the same window as the code, with repository evidence attached when Codoro can verify it.

04 Chat

Your team and the agent in the same channel

Repository-scoped channels and threaded code context backed by organization access controls and history retained until the conversation is deleted.

Design

Every frame is a file. The canvas edit is the diff.

The Design tab opens manifest-declared frame previews, and each one is bound to the file it describes — Dashboard — desktop is app/(dash)/page.tsx, Budget card is components/budget-card.tsx. The properties panel edits the tokens the app already ships: the 1px hairline gap, the zero radius, the 1240 maximum width, read from globals.css rather than transcribed into a second document. Apply to code quotes an estimate, writes the change as a diff, and commits nothing until you approve it.

No handoff

Nothing to reimplement

A designer makes a picture, a developer builds it again in code, and the two drift from that moment on. That is the expensive part, and it is not a shortage of AI. Here the frame stays bound to the source path and the edit lands as a reviewable proposal, so the relationship is explicit instead of hidden in a handoff.

Real tokens

Design against what the code uses

Colour, spacing and type come from the stylesheet the app is built with, in both themes. Change one on the Tokens tab and the change arrives in that stylesheet as a diff, which is why the canvas and the running app cannot disagree.

Priced like a run

An estimate before it writes

Apply to code shows what the edit will cost, reserves it, and settles against real usage after — the same balance and the same per-run cap as a typed request or a spoken one. One ledger, not one per surface.

Voice

Hear the diff, and see when the microphone is active.

The desktop voice surface exposes microphone permission and input level, and it can read a reviewed diff aloud with macOS system speech. Speech-to-text controls are shown only on a target where recognition is actually available. The richer conversation below is the interaction design being tested, not a promise that every native build can transcribe.

◉ Listening01:12 · $0.04 this call
You

Why is the budget test failing?

Codoro$0.02

reserve() only checks the run cap. The failing case crosses the day cap, so nothing stops it. Two lines in lib/budget.ts.

You

Do it, but use Haiku.

Codoro$0.01

Switched to Haiku 4.5. Taking the minimum of the run cap and what is left of the day, then rerunning the domain tests.

You

Read me the diff.

Codoro$0.01

Two added lines: spentToday for the actor, and a ceiling that is the smaller of the two caps. The comparison now uses the ceiling.

End callHands-freeHold space to talk
Interaction target — microphone state and local narration ship first; transcription remains target-gated.
Shared text ledger

The cost is on the transcript

When recognition produces a text request, the model reply uses the same governed text call and ledger as the composer. Microphone capture and local narration do not invent a second hosted-audio charge.

Target-gated input

Hands-free, or hold space

The app reports permission and level state first. Hands-free and hold-to-talk remain hidden when the native host has no supported recognition engine, so a visible control is one the target can execute.

It reads the diff back

Review without looking away

macOS system speech can narrate the reviewed diff locally before it is applied. The text and source diff remain the review record; synthesized audio is not uploaded or retained as a second transcript.

This page never asks for your microphone. Voice runs in the app.

One task, one model. Not one model for everything.

Scaffolding a component and reasoning through a race condition do not cost the same and should not be priced the same. Codoro puts featured models first, makes every available Vercel AI Gateway model searchable, carries the conversation across the switch, and shows the rate before the run.

Anthropic
Claude Fable 5
Claude Opus 5
Claude Sonnet 5
OpenAI
GPT-5.6 Sol
GPT-5.6 Terra
GPT-5.6 Luna
DeepSeek
Codoro Fast
DeepSeek V4 Pro
Google
Gemini 2.5 Pro
Gemini 3.7 Flash
xAI
Grok 4.6
Grok 4.3
Moonshot
Kimi K2.7 Code
Kimi K2.6
Cost control

A cap that holds, not a dashboard you check.

Every run reserves its estimated cost before the first token and settles against the real usage after. When a cap is reached the run pauses and offers you a cheaper model — it does not quietly downgrade, and it does not keep going.

Per run
$2.00
default cap, editable per task
Per day
$25.00
per developer, set by the team owner
Markup on your own keys
0%
provider bills you directly

Four plans. Tokens are metered, the IDE is not.

Prices in USD, billed monthly
Hobby
$0
Includes Your own API keys

Use the desktop IDE with your own Anthropic, OpenAI, DeepSeek, Google, xAI, Moonshot, Z.ai, Alibaba or Mistral key. Codoro takes nothing for those tokens — your provider bills you directly. Hosted models are on the paid plans.

Pro
$20
Includes $20 monthly Codoro credits

Every shipping desktop feature with a monthly retail-credit balance. Hosted usage is debited at the per-model retail rate disclosed in the selector before you run it.

Pro+
$60
Includes $60 monthly Codoro credits

The same features with three times the allowance, for people whose day is mostly long autonomous runs on frontier models.

Ultra
$200
Includes $200 monthly Codoro credits

Ten times Pro's allowance, priority on new models, and per-repository caps for people running several agents at once.

Teams are $40 a seat, on one pooled budget with a per-seat ceiling the owner sets and a spend ledger by developer, repository and model. Top-ups beyond your allowance are prepaid, never auto-charged, and debit the published retail rate for the selected model — or bring your own API key and pay Codoro nothing for tokens at all.

Install it, point it at a repository, set a cap.

Get Codoro for macOS