aionedge.
Jev project · Agent tooling

tiershift

iamvatsalpatel/tiershift

Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.

View on GitHub ↗
GitHub stars
3 as of 2026-09-22
Forks
1
Language
TypeScript
License
MIT
Created
2026-09-17
Last updated on GitHub
2026-09-21
Added to AionEdge
2026-09-19
Built by this developer
Vatsal Patel

What Jev does in tiershift

The project describes itself this way: Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python. In the Agent tooling category, Jev typically decides which tool, skill or model to use next, whether a step is finished, and whether an action is risky enough to stop.

Verification

Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.

Topics

How Agent tooling projects use Jev

Agent tooling is where Jev sees the most experimentation. These projects sit inside coding agents and assistants such as Claude Code, Codex and Pi, and hand the many small, repetitive choices an agent makes to a fast decision model, leaving the large model free for reasoning and writing.

Also listed in: Routing & Cost Optimization.

Related Jev projects in Agent tooling

  1. jev-predict-skillDanielKillenberger/jev-predict-skillAn Agent skill recipe that predicts another skill’s closed-set outcome from its rules and evidence.★ 3
    HTML
  2. jev-judgmentHyunjunJeon/jev-judgmentAdds judgment checks for authorization, operation risk, and failure causes to coding Agents.★ 3
    Python
  3. jevexjvsteiner/jevexAn Agent experiment where Jev directs a tool loop, a chat model fills arguments and prose, and MCP tools execute.★ 3
    Python
  4. todo-jevmaker-KK/todo-jevA task-routing experiment combining skill conditions and environment checks to suggest rules, skills or a large model.★ 3
    Python
  5. jev-swap0xjba/jev-swapScans TypeScript, JavaScript and Python for decision-like LLM calls, generates Jev replacements and shadow-tests recorded traffic.★ 2
    HTML
  6. jev-scoutAkashPriyadarshii/jev-scoutA repository and Rust crate search tool that asks Jev to score and select retrieved candidates for a request.★ 2
    Rust

See all 172 Agent tooling projects →

Where we found it