cd /news/ai-agents/show-hn-jev-routing-coding-tasks-to-… · home topics ai-agents article
[ARTICLE · art-133118] src=github.com ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Show HN: Jev routing coding tasks to Grok Build or Codex Astra

A developer released Jev, a local prototype router that sends complex or uncertain coding tasks to Codex Astra and contained mechanical work to Grok Build. The router asks Jev three typed questions in one request — a choice between Grok Build or Codex Astra, a complexity score from mechanical to high consequence, and a boolean on whether planning or investigation should precede code changes — and defaults to Astra when Jev is uncertain, the complexity score is high, or planning is likely. Grok Build runs locally on default model grok-4.6 and Codex Astra runs locally as model gpt-6-astra, with Codex Astra launching ephemerally in a read-only sandbox and Grok Build running in plan mode with web search and subagents disabled; neither route edits code in the prototype.

read1 min views1 publishedSep 17, 2026
Show HN: Jev routing coding tasks to Grok Build or Codex Astra
Image: Michielbdejong (auto-discovered)

This is a throwaway local prototype for one question: can Jev reliably send complex or uncertain coding tasks to Codex Astra while routing contained mechanical work to Grok Build?

The router uses Jev only for the decision. It asks three typed questions in one request:

  • Choice: Grok Build or Codex Astra
  • Score: complexity from mechanical to high consequence
  • Boolean: whether planning or investigation should happen before code changes

The final policy is intentionally conservative. If Jev is uncertain, the complexity score is high, or planning is likely, the task goes to Astra.

  • Grok Build: installed locally, default modelgrok-4.6
  • Codex Astra: installed locally as modelgpt-6-astra
cd /Users/simsies/github/jev-model-router-demo
npm install

Add a Vercel AI Gateway key to the already gitignored .env.local:

AI_GATEWAY_API_KEY=your_key_here
npm run demo

This classifies six tasks in parallel and prints the chosen harness, route probability, complexity score, planning probability, and latency. It does not launch either coding agent.

npm run route -- "Add an aria-label to the close button and run its existing test."
npm run route -- \
  "Trace the intermittent authentication failure without weakening security." \
  --cwd /Users/simsies/github/example-project \
  --launch

Launches are deliberately safe for the demo:

  • Codex Astra runs ephemerally with a read-only sandbox.
  • The Codex launch accepts an explicitly selected non-Git demo directory.
  • Grok Build runs in plan mode with web search and subagents disabled.

Neither route edits code in this prototype. After the routing policy is calibrated on real tasks, execution permissions can be designed separately.

Jev requests enable Zero Data Retention and disallow prompt training. Do not paste secrets, credentials, private customer data, or unredacted logs into a filmed task.

── more in #ai-agents 4 stories · sorted by recency
── more on @jev 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-jev-routing-…] indexed:0 read:1min 2026-09-17 ·