Repo · Coding & code review

jevXagent

When Jev meets LLM — Transparent proxy that makes AI coding agents 3× faster and 80% cheaper.

Open github.com ↗

From the repository

When Jev meets LLM — Transparent proxy that makes AI coding agents 3× faster and 80% cheaper. Cut response times from 2.4s to 890ms with Line J architecture.

ai-agentsai-cost-reductionclaude-codecoding-agentcost-optimizationdeveloper-tools-ai-agentintelligent-routingjevjev-apijev-integrationjev-modeljevproxyjevxagentkilo-codellm-proxyproxy-servertokentoken-optimizationtoken-reductionvscode

How builders describe it

When Jev meets LLM — Transparent proxy that makes AI coding agents 3× faster and 80% cheaper. Cut response times from 2.4s to 890ms with Line J architecture.

jevXagent is a localhost proxy that sits in front of Claude Code, Codex, Kilo Code and Cline. It asks Jev to classify the prompt first, then injects that verdict into the agent's system context so the main model skips re-deriving the same classification.

The decision Jev makes

Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.

Where it fits

Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 450 coding & code review projects →

Related projects