Spend your strongest model on the tasks that need it. ModelRudder adds experimental model routing to native coding tools, while they retain their tools, approvals and workspace permissions.
Free local community preview · MIT licensed · macOS, Linux/WSL and Windows preview
Use your own native provider account and your own TypeSafe Jev API key. This preview requires no ModelRudder account or subscription. Provider charges and usage limits still apply. Clef support is not included.
Experimental Claude preview: Claude Code now has a native Mods adapter for per-user-turn Haiku/Sonnet/Opus routing, with one decision held through each tool loop. The preview.4 installer bundles smart-claude alongside smart-codex; read Claude support, installation and verification limits first. Native Claude effort, model availability and safety fallback remain authoritative. No subscription limit is bypassed, and savings are not guaranteed.
Copy this entire prompt into Codex. It will install ModelRudder and open the local configuration file; you enter your Jev key privately in the editor.
Install ModelRudder on this computer so I can use model routing in Codex.
Use the official release: https://github.com/cybrking/modelrudder/releases/tag/v0.1.0-preview.4
Read the README and docs/AGENT_INSTALL.md at that release tag and follow them.
Detect my OS and check Node.js and Codex. Install missing prerequisites using
the official instructions; ModelRudder requires Node 24+ and a supported Codex
version. Preserve existing credentials and configuration, and explain any
incompatible Codex version before changing it.
Download the release installer and SHA256SUMS, verify the checksum, install
for my user account, and add its launcher directory to my user PATH without
removing existing entries. Verify smart-codex --help.
Run smart-codex setup to open my private Jev configuration in a local editor.
Show me https://console.typesafe.ai/keys so I can sign up and get my own key.
Never read or print the key file or ask me to paste a key into chat. Leave new
classification disabled until I enter the key and explicitly enable it.
Check my Codex login without replacing it. If login is needed, guide me through
the official codex login flow. Run smart-codex doctor, explain anything still
needed, and give me the command to start in a fresh terminal. Do not submit
paid model tasks automatically.
If an editor cannot open, Codex can give you the file path to open manually. Detailed agent instructions cover Windows, Linux/WSL and macOS.
Copy this entire prompt into Claude Code. It will install ModelRudder and open the local configuration file; you enter your Jev key privately in the editor.
Install ModelRudder on this computer so I can use model routing in Claude Code.
Use the official release: https://github.com/cybrking/modelrudder/releases/tag/v0.1.0-preview.4
Read the current Claude installation guides before continuing:
https://github.com/cybrking/modelrudder/blob/main/docs/AGENT_INSTALL.md
https://github.com/cybrking/modelrudder/blob/main/docs/CLAUDE_CODE.md
Detect my OS and check Node.js and Claude Code. Install missing prerequisites
using official instructions; ModelRudder requires Node 24+ and Claude Code
2.1.293 or newer within the 2.1.x line. Preserve existing credentials,
configuration and permissions. Explain any incompatible version or login
before changing it. Codex is not required to use smart-claude.
Download the release installer and SHA256SUMS, verify the checksum, install
for my user account, and add its launcher directory to my user PATH without
removing existing entries. The smart-codex-named preview.4 installer bundles
both smart-codex and smart-claude; no source build is needed. Verify
smart-claude --help. Do not replace plain claude or an unmanaged launcher.
Run smart-claude setup to open my private Jev configuration in a local editor.
Show me https://console.typesafe.ai/keys so I can sign up and get my own key.
Never read or print the key file or ask me to paste a key into chat. Leave new
classification disabled until I enter the key and explicitly enable it.
Explain that observe/auto sends eligible task text and bounded earlier task
excerpts to TypeSafe, and requires the direct Jev classifier.
Check my native Claude login without replacing it. If login is needed, guide
me through the official claude auth login flow. Run smart-claude doctor and
explain anything still needed. Preserve native plugin trust and organization
policy; do not bypass either. Give me smart-claude --routing observe to run
in a fresh terminal after setup. Do not submit model tasks or classifier
requests automatically.
If an editor cannot open, Claude Code can give you the file path to open manually. Once you have checked observe mode, try smart-claude --routing auto, or use smart-claude --model sonnet for pinned mode without Jev classification. See Claude support and verification limits; live task quality and full cross-platform TUI behavior remain unverified.
- Node.js 24 or newer, installed separately. The installer does not bundle Node, Codex or Claude Code.
- macOS, Linux/WSL, or Windows 11 with PowerShell. Native Windows support is a preview; ModelRudder's full Windows TUI has not been validated. WSL is an alternative if your native setup fails; install and sign in separately inside WSL. See OpenAI's Windows guidance .
- For
smart-codex, an independently installed Codex CLI. Exactly versions0.159.3, 0.160.1 and 0.161.0 have recorded protocol evidence and are accepted by this preview. Full interactive TUI compatibility is not certified; other versions are rejected. See therelease-readiness results for completed checks and remaining gaps. Claude's separate requirements are inCLAUDE_CODE.md . - For
smart-codex, native ChatGPT login throughcodex login. Forsmart-claude, an independently installed Claude Code 2.1.293+ within 2.1.x and nativeclaude.ailogin; Codex is not required. - Your own TypeSafe Jev API key for observe/auto modes. Pinned mode works without classification.
OpenAI describes continuation of existing local/open-source app-server applications separately from commercial/hosted authentication. This release does not establish permission to operate a paid subscription-auth service. See OpenAI guidance. ModelRudder is an independent project, with no claimed provider endorsement.
Download the installer and SHA256SUMS from Releases. Keep them in the same directory and verify the checksum before running the installer filename shown on that release:
shasum -a 256 -c SHA256SUMS
node -- ./smart-codex-RELEASE_ID-install.mjs
Replace RELEASE_ID with the actual release ID in the downloaded filename. Obtain both files from this project's trusted release page; a checksum alone does not authenticate a publisher. The installer needs no checkout or npm download and includes the ws dependency and license. On macOS/Linux, it installs versioned runtime files under ~/.local/share/smart-codex and a launcher under ~/.local/bin; add that bin directory to PATH. It does not replace plain codex or an unmanaged launcher.
On Windows, use PowerShell's Get-FileHash -Algorithm SHA256 and compare the installer hash to its exact filename in SHA256SUMS, then run node -- .\smart-codex-RELEASE_ID-install.mjs. The default runtime, launcher and configuration are under %LOCALAPPDATA%\ModelRudder\runtime, \bin and \config\env, respectively. Use the paths printed by the installer and add its launcher directory to your user PATH. Agent-assisted installation instructions are in AGENT_INSTALL.md.
Alternatively, build from a trusted source checkout:
npm ci --ignore-scripts
npm test
npm run typecheck
npm run install-cli
Create and open your private Jev configuration in a local editor:
smart-codex setup
Setup preserves an existing file. Agents and terminals without a desktop can use smart-codex setup --no-open to create the template and print its path without opening an editor. The configuration starts with three editable settings and classification disabled:
TYPESAFE_API_KEY=
ALLOW_JEV_CLASSIFICATION=false
SMART_CODEX_CLASSIFIER=direct
If needed, sign up and create your key at the official TypeSafe dashboard, linked by the Jev quickstart. Enter your key privately in the local editor and change ALLOW_JEV_CLASSIFICATION from false to true after reviewing the data flow below. Keep credentials out of agent chat, command arguments and source control. Existing exported environment variables take precedence over the configuration file. Leaving ALLOW_JEV_CLASSIFICATION=false keeps Jev disabled; pinned mode remains available.
smart-codex doctor
smart-codex --routing observe --effort-mode fixed
Observe mode gets route recommendations while Sol executes the task. Inspect your results before trying experimental automatic routing:
smart-codex --routing auto --effort-mode auto
Automatic mode chooses among Luna, Sol and Astra at each eligible new user turn and keeps that choice throughout its tool loop. Uncertain or unavailable classification keeps the fallback. Media, native references and unobserved history can prevent downgrading. The next auto/observe turn overrides native model-picker choices. An explicit --model selects pinned mode unless --routing is also supplied.
To use a pinned model without sending tasks to Jev:
smart-codex --routing pinned --model gpt-6.1-sol
In auto/observe mode, direct classification sends the current eligible text task and up to two bounded earlier task excerpts to TypeSafe. Anything pasted into that text, including source code or secrets, is included. The adapters do not automatically send repository files, assistant output or attachments to the classifier. Native Codex and Claude Code send their normal model inputs to their providers under your own account terms. Claude requires the direct classifier; the current hosted gateway has only a Codex rubric.
The child process does not receive the Jev key from ModelRudder's classifier environment. Each native tool manages its own login. Claude's mod contacts a launcher-local authenticated loopback bridge; it does not proxy Claude model requests or obtain Claude credentials. Local reports contain routing/usage metadata rather than task text; configuration and logs remain on your machine. Review provider policies before sending confidential content. The community client has no ModelRudder telemetry or hosted billing requirement.
smart-codex report
smart-codex outcome --result accepted
smart-codex logs cleanup --older-than-days 30
Outcome markers are your own assessment, not independent validation. Cleanup is a preview unless --apply is supplied. Tokens and reference-price comparisons are estimates; they do not establish savings on a subscription bill or verified task quality.
For source users, upgrade by pulling an approved release, running npm ci --ignore-scripts, and rerunning npm run install-cli. Standalone users can install the next trusted release installer. Restart active launchers after an upgrade. Use the installed maintenance command:
node -- ~/.local/share/smart-codex/current/src/install-cli.ts --list
node -- ~/.local/share/smart-codex/current/src/install-cli.ts --rollback RELEASE_ID
node -- ~/.local/share/smart-codex/current/src/install-cli.ts --uninstall
On Windows, retain the verified installer and use node -- .\smart-codex-RELEASE_ID-install.mjs --list, --rollback RELEASE_ID or --uninstall instead. Repeat any custom install-path flags used originally.
Uninstall retains your private configuration and local state. Remove those manually if you intend to discard them.
Automatic routing is experimental: classifier confidence is not a coding success probability. Full native TUI behavior, task quality and a general Codex compatibility range remain unqualified. Start with observe mode, inspect changes and run your own tests. The preview is not a production SLA or a guaranteed savings claim. See release evidence.
npm ci --ignore-scripts
npm test
npm run typecheck
npm run package:pilot -- dist/delivery
Client CI runs offline fixtures and a no-inference native Codex protocol probe on Windows, Linux and macOS with Node 24 and 26; check the workflow and individual results for the operating systems tested. It makes no paid inference calls. npm run test:native-protocol is an optional installed-Codex check; it submits no model turn and does not certify the TUI, including on Windows.
Read contributing and security reporting. Licensed under MIT; ws retains its upstream MIT notice.
Daily upstream checks detect new stable Codex and Claude Code releases once a day and run isolated candidate checks on macOS, Linux and Windows. Review the workflow reports before changing supported versions.