openchamber
Open-source workspace for running and reviewing AI coding agents across devices, with an optional Jev-based automatic model router.
Overview
OpenChamber is an open-source workspace for running and reviewing AI coding work on desktop, web, VS Code and mobile. Features include Session Goals that keep an agent working until a finish line is met, Multi-run across up to five models with a Fusion option to combine results, guided Changes Walkthroughs of large diffs, a Preview pane for inspecting a running app, GitHub issue-to-PR flows, cross-device continuity and an end-to-end encrypted Private Relay.
Per the list summary, its optional automatic model router uses Jev to classify a message before selecting a configured model and reasoning level. The fetched README excerpt does not document the router, so the classification labels are inferred. It suits developers juggling multiple agent sessions who want cheaper models on simple turns.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which configured model and reasoning level should handle this message?(inferred) | — |
How it works
- User sends a message to a session.
- Optional router asks Jev to classify the message.
- Select the configured model and reasoning level.
- Agent runs with that model.
Strengths
- Router is optional.
- Rich multi-device agent workspace.
Caveats
- Router details known only from the list summary.
- Jev routing requires a TypeSafe key.
At a glance
- Type
- Project
- Status
- production
- Language
- TypeScript
- Runtime
- desktop, web, VS Code, mobile
- Has code
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
OpenChamber’s optional automatic model router uses Jev to classify a message before selecting a configured model and reasoning level.
logicrw/awesome-jev-projects
Frequently asked questions
How does OpenChamber use Jev?
Its optional model router classifies messages with Jev to pick a model and reasoning level.
Is the router on by default?
The list summary describes it as optional.
What else does OpenChamber do?
Runs, compares and reviews AI coding sessions across devices.
Related projects
Local-first routing engine for long-running agent tasks that uses a Jev decider to pick a model group per turn.
PluginproductionRust, TypeScriptOpen-source AI gateway for 100+ LLMs that can use Jev to classify requests for complexity routing and to compact tool results.
ProxyproductionPython- jev-router★ 593
Per-turn model routing for Claude Code and Codex: wraps the real CLI and lets Jev send simple turns to fast models and hard ones to strong.
ProxybetaJavaScript - jev-codex-router★ 274
Per-call router for Codex where Jev picks the model and thinking effort for every model call, including tool continuations.
ProjectbetaPython Model router where Jev classifies each request's task family and code picks the cheapest capable model on a cost Pareto chain.
ProjectbetaTypeScriptClaude Code mod that sets model and effort per turn and subagent from a prompt classifier: Jev by default, or Clef, OpenAI or Ollama.
Proxybeta