aionedge.
Jev project · Agent tooling

jev-swap

0xjba/jev-swap

Scans TypeScript, JavaScript and Python for decision-like LLM calls, generates Jev replacements and shadow-tests recorded traffic.

View on GitHub ↗See the Jev code ↗Project website ↗
GitHub stars
2 as of 2026-10-05
Forks
0
Language
HTML
License
MIT
Created
2026-09-24
Last updated on GitHub
2026-10-05
Added to AionEdge
2026-10-05
Built by this developer
0xjba
github.com/0xjba

What Jev does in jev-swap

Uses typed Jev decisions with confidence-gated fallbacks. Savings estimates and shadow comparisons depend on the workload; conversion is not proof of equivalent production behavior. Catalog verification inspected README and source; the application was not independently runtime-tested.

Verification

Verified. We confirmed this repository through the GitHub API and located the code that calls Jev at a pinned commit: view the Jev code ↗. Upstream code changes over time, so check that the file still exists at the current commit before citing it.

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.

Related Jev projects in Agent tooling

  1. jev-scoutAkashPriyadarshii/jev-scoutA repository and Rust crate search tool that asks Jev to score and select retrieved candidates for a request.★ 2
    Rust
  2. jev-workbenchmolis-ai/jev-workbenchDefines, tests, and publishes Jev decision functions in a local UI so backends and Agents can call fixed versions.★ 2
    TypeScript
  3. jev-bugfixxiaoxiaomugong/jev-bugfixCodex bug-investigation skill with optional Jev ranking of manually collected code candidates.★ 2
    Python
  4. jev-predict-skillDanielKillenberger/jev-predict-skillAn Agent skill recipe that predicts another skill’s closed-set outcome from its rules and evidence.★ 3
    HTML
  5. jev-judgmentHyunjunJeon/jev-judgmentAdds judgment checks for authorization, operation risk, and failure causes to coding Agents.★ 3
    Python
  6. jevexjvsteiner/jevexAn Agent experiment where Jev directs a tool loop, a chat model fills arguments and prose, and MCP tools execute.★ 3
    Python

See all 172 Agent tooling projects →

Where we found it