Organization repository on GitHub
outcome-aware & adaptive model routing for coding agents with deterministic cache powered by Jev
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Tools & CLIs
Jevia
An open-source, local-first model router for coding harnesses: Jevia asks Jev for a capability tier per task, applies your safety policy, and keeps recorded execution history in your project or database so later routes learn from outcomes.
- Stars
- 10
- Language
- Rust
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- assistant-ui
- Last verified
- Oct 2026
Highlights
- Chooses a capability tier per task, applies your safety policy, and records execution history for future routes.
- Works with Claude Code, Codex, OpenCode, Gemini CLI, Cursor Agent, or a custom harness.
- Installs from a checksum-verified macOS or Linux binary; jevia init, jevia check and jevia route set up and verify routing.
- jevia run executes and records automatically; jevia feedback reports a known result for route-only integrations.
- Experimental, MIT-licensed: CLI 0.1.9 with a separately versioned Node SDK at 0.1.3.
Quickstart
bash
curl -fsSL https://jevia.dev/install.sh | sh
jevia init
export TYPESAFE_API_KEY="your-key"
jevia check
jevia route "investigate the failing integration test"Watch out
Grounded on a truncated README and GitHub metadata captured 2026-10-15; the digest ends mid-sentence in the harness section, so adapter details beyond the built-in presets come from the summary. The project labels itself experimental, and a managed control plane is explicitly not part of the repository.
Questions about this entry
Short answers drawn from the linked project or page.
Most routers stop after choosing a model. Jevia closes the loop: a task is routed, the harness runs it, observations and optional feedback become known outcomes, and that history informs later routing decisions.
Jev picks a capability tier for each task and Jevia applies your safety policy on top; your adapter maps that tier to a concrete model and command for the harness you already use.
Claude Code, Codex, OpenCode, Gemini CLI, Cursor Agent, or a custom harness through explicit --command and --arg values. Built-in presets supply only the executable and argument shape; model IDs and credentials stay yours.
The CLI installs from a checksum-verified macOS or Linux binary without Rust or Cargo, or via PowerShell on Windows. Routing requires a TYPESAFE_API_KEY; policy, cache and history stay local in your project or database.
No. The README is explicit that your verifier or feedback decides success and Jevia does not grade its own work; a process exit remains an observed fact, and extra verification is opt-in.
It is experimental. The README says the CLI, typed routing contract, local outcome store, harness adapters and Node.js SDK are available today, but a managed control plane is not part of the repository.
jevia run records automatically with no manual feedback step; for route-only integrations you can report an outcome later with jevia feedback <run-id> success, and jevia stats and jevia runs summarise the stored history.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.
FacebookClinicnotes
X: OpenRouter Decision Model Rankings
X: herdr + jev, an agent router
X: A group chat bot with decision room routing
More Jev resources like this
A macOS wrapper for Codex that has Jev pick the model and reasoning effort for the first task in a thread, pins that route so later turns reuse their model cache, and offers a menu bar app for routing preferences and quota-aware selection.
Jev Tools & CLIs#community#catalog-import#logicrw
Rust coding-agent harness (MIT, ~20k stars) whose crates/jcode-base/src/jev.rs is a typed TypeSafe Jev decision transport, used for memory pruning (memory_jev.rs), browser navigation (browser_jev.rs), and voice routing (voice_intent.rs) with separate provider selectors per purpose.
Jev Tools & CLIs#community#rust#coding-agent
Community
1jehuang/jcodeRust
1jehuang/jcodeRustA Rust CLI that streams Kubernetes logs, triages them with local offline rules or typed Jev questions online, and presents an interactive terminal UI plus JSON reports. Collection is read-only and every judgment is advisory.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
sunil-sadasivan/jevernetesGo
sunil-sadasivan/jevernetesGoA Rust CLI that gates shell pipelines on a Jev-style yes/no judgment: it reads text on stdin, asks the classifier a question, and passes the text through only when P(yes) clears a threshold — the README calls it smarter cron.
Jev Tools & CLIs#community#github#rust
Community
gordonbrander/jevgateRust
gordonbrander/jevgateRustA browser automation CLI for AI agents: drive Chrome with natural language in an interactive terminal or structured commands like jevb page act, signed in with a TypeSafe or OpenRouter key. Prebuilt packages target macOS Apple Silicon; Node.js 22+.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
mrlyk/jev-browserRust
mrlyk/jev-browserRustA Rust CLI that searches code by meaning with Jev: describe a concept in plain English and get relevant files, line ranges, confidence scores and source snippets, with tunable file and match thresholds plus retry handling.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
peu77/jevfindRust
peu77/jevfindRustFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.