The coding agent runtime · pre-launch

Give it a goal.
Get it back, finished.

CodeRight isn't a coding chat you babysit. It runs the goal across a roster of models, reviews the work, rejects a false "done", remediates, and logs every step — for as long as the goal actually takes. Minutes, not a magic instant.

runs in the background — you don't have to watch it
RUN · Add OAuth login + tests to the APIworking…
00:00goal received · queued to Conductor
00:06Architect (Claude) planned · 3 subtasks
01:24Code Worker (DeepSeek) wrote auth.rs · +142
03:10Red Team (GLM) flagged · tests missing
04:02Jury reviewed · 2 of 3 pass
04:03Arbiter REJECTED · tests never ran
05:48remediation · tests added, suite green
06:31Arbiter PASSED · goal verified ✓
Async
runs in the background
Logged
every step, timestamped
Verified
finishes when the goal is met
No Electron
Rust daemon + Tauri, local

A goal worth giving an agent is worth more than three minutes of attention. So CodeRight takes the time it needs — and tells you exactly what it did.

— it stops when the goal is done, not when the model goes quiet
The Completion Arbiter

"The model stopped talking" is not "done".

Every other harness ends the run when the model goes quiet. CodeRight asks a different question — was the goal met? — and these are the answers that make it say no.

Tests never ran.

Code changed, suite untouched. Rejected — re-run before it counts.

Goal half-met.

Login added, the tests the goal asked for weren't. Sent back.

Jury split.

Reviewers disagree on correctness. No quiet pass — it resolves first.

Nothing actually changed.

A confident "done" with an empty diff. Caught, not trusted.

Anatomy of a run

What happens while you're not watching.

Route

The Conductor splits the goal.

It plans with the Architect, then routes subtasks across role-pinned specialist models — not one model doing everything.

Build & attack

Workers build; the Red Team breaks.

A Code Worker writes the change; a Red Team model attacks it and surfaces what's missing before it's called done.

Judge

An independent jury reviews.

Different models than the author validate the artifact. Verdicts are hash-bound — a pass can't be reused on changed code.

Gate

The Arbiter rejects a false "done".

Tests never ran? Goal half-met? It says so, spawns remediation, and re-checks — until the goal is actually verified.

The roster

Pin any model to any role. Swap freely.

Bring your own API keys — works with any OpenAI-compatible model, via OpenRouter · NIM · Groq · Cerebras. Keys stay local and encrypted.

Architect ClaudeCode Worker DeepSeekRed Team GLMResearch Kimi K2Historian MistralArbiter Claude
Built to improve itself

Built to promote models on evidence.

An evolution layer is designed to benchmark candidates and promote the model that does a role better — governed, logged, never silent.

Local-first

No account, no telemetry.

CodeRight's control plane runs locally. Your code is not uploaded to CodeRight servers; model requests go only to the provider or local endpoint you configure.

Native & light

Rust daemon + Tauri.

No Electron — tens of megabytes resident, not gigabytes. A runtime that lives quietly in the background.

Pricing

Free to run. Pay once to orchestrate.

CodeRight is free as a single-model coding agent. The full multi-model runtime — Conductor, jury, Completion Arbiter — plus ongoing updates live in Pro: one payment, no subscription, BYO keys.

Free
$0
Single model · BYO key · forever
  • One model, your key — a capable single-agent coding loop
  • Sessions, tools, permission system, MCP, compaction
  • Native Rust daemon + Tauri — local, no telemetry, no account
  • Security updates
CodeRight Pro
$199$249
Founders price · one-time · then $249
  • Everything in Free, plus the full runtime
  • Multi-model orchestration — Conductor, roster, jury, Completion Arbiter
  • Evolution layer, A2A control surfaces, schedules
  • Feature updates within the major version
  • Unlimited personal devices · perpetual license
Reserve the founders price →

BYO keys means model usage is billed by your provider, never by us.

CodeRight Pro$199 onceUnlimited personal devices. $249 standard after founders pricing.
CodeRabbit Team$24/user/moAbout $288 per developer every year when billed annually.
Greptile / CodacyRecurring seatsUseful SaaS tools, but priced as ongoing per-developer subscriptions.

See the full pricing comparison · Compare CodeRight vs CodeRabbit

Pre-launch · BYO keys · native

Hand it the goal. Walk away.

CodeRight is pre-launch. Leave your email for the beta — we'll email you when the build is ready, and you can optionally tell us what you're using today.

No spam, no list-selling. Launch and release updates only.

Investing or partnering? hello@coderight.cc