Organization repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Jev Planner
A CLI that produces repository-aware implementation plans from two or more agents drafting independently, then has Jev score completeness, feasibility and risk coverage, decide whether cross-review is worth it, and select a finalizer that merges the strongest ideas.
- Stars
- 0
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- rxova
- Last verified
- Oct 2026
- Languages
- TypeScript
- Platforms
- CLI
- Capabilities
- Open sourceRequires API key
Highlights
- Two or more agents draft plans independently: agent CLIs inspect the repository, chat APIs get a snapshot of it.
- Jev scores completeness, feasibility and risk coverage, decides whether cross-review is worth it, then selects a finalizer for the merged plan.
- Codex and Claude are defaults; DeepSeek, Kimi and GLM are supported, and one provider can run twice under names like codex:sol,codex:terra.
- --mode fast judges each draft alone as it arrives and takes the first Jev accepts; every round is saved under .jev-planner/<run>/.
- Needs Node.js 20.19+, credentials for at least two agents and a TypeSafe key; a jev-planner.json pins options and never holds a key.
Quickstart
bash
npm install -g jev-planner
export TYPESAFE_API_KEY='your-key'
jev-planner doctorWatch out
Grounded in the truncated repository README and GitHub metadata reviewed on 2026-10-15; no benchmark or pricing figures are published, the useful-controls list is cut off after --mode, and running it needs paid access to at least two agent providers plus a TypeSafe key. MIT, 0 stars.
Questions about this entry
Short answers drawn from the linked project or page.
It produces repository-aware implementation plans from two or more agents that draft independently and then challenge each other, with Jev scoring the drafts and making the final call on a single merged plan.
Jev scores each draft on completeness, feasibility and risk coverage, decides whether a cross-review would improve the plans, and then selects a finalizer that merges the strongest ideas, unless one reviewed plan already stands alone.
npm install -g jev-planner, export TYPESAFE_API_KEY, then jev-planner doctor. Run it from the repository you want inspected, for example jev-planner "Add per-user rate limiting to the public API". Node.js 20.19 or newer is required.
Codex and Claude are the defaults; DeepSeek, Kimi and GLM are also supported through their chat APIs. Use --agents to choose, and one provider can run as two named agents, for example --agents codex:sol,codex:terra.
Fast mode short-cuts the cross-review: Jev judges each draft alone as it arrives, and the first one it accepts becomes the plan. The normal mode can send drafts through a mutual review round first.
Every round's plans and Jev's verdicts go under .jev-planner/<run>/; --rounds-dir moves that, --no-rounds skips it, and --json emits structured output. A jev-planner.json in the repo pins flags for every run and never holds a key.
rxova's project under MIT; 0 stars at review time. It needs Node.js 20.19+, credentials for at least two agents (already-logged-in CLIs or chat API keys) and a TypeSafe API key, and the README publishes no benchmarks or pricing.
More Jev resources like this
An npm CLI that scans TypeScript, JavaScript and Python codebases for LLM calls that are really decisions, converts them into Jev modules with confidence-gated fallbacks, and shadow-tests them on recorded traffic before you swap.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
0xjba/jev-swapHTML
0xjba/jev-swapHTMLLatitude is an open-source observability platform for AI agents: one line of telemetry captures traces, failing traces group into tracked signals, and fixes are dispatched to coding agents and replayed against real traces.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
latitude-dev/latitude-llmTypeScript
latitude-dev/latitude-llmTypeScriptAn 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.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
assistant-ui/jeviaRust
assistant-ui/jeviaRustAn ultra-lean supervisor extension for the pi coding agent: zero-token regex guardrails stop destructive commands, a done-check tracks test verification, and a Jev semantic gate reviews diffs before disk writes.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
bismawy/pi-jev-eyeTypeScript
bismawy/pi-jev-eyeTypeScriptMaykana's free tool that lets a cheap AI test a web app like a person: write checks in plain sentences, Jev picks the next step from a short list, and below 80% confidence it stops and hands over to a human instead of clicking. A DeepSeek vision pass reports visual defects.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
elshinq/jevaluateJavaScript
elshinq/jevaluateJavaScriptModeration for communities and apps, powered by Jev: every message gets a probability for spam, scam, harassment, nsfw, doxxing and more, plus rules in plain English. Thresholds and actions are yours, and flag-only is the default.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
ohernandezdev/jevmodPython
ohernandezdev/jevmodPythonFrom 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.