devwithjev
— reading now— views
Submit a build

Jev-Based Tool Output Compaction

Jerry the Martian says Jev-based compaction scores old tool outputs, keeps what is needed, and parks the rest on disk. He says it uses 30 to 55% less context and costs $0.0005 a pass.

View on X cost$0.0005 a pass
Jerry the Martian@jerry543𝕏
If you use omp, you're missing out on jev based compaction It helps your agent optimize token usage with 30 to 55% less context. $0.0005 a pass What it does: - Scores every old tool output with Jev - Keeps what's needed - Parks the rest on disk - Remembers its decisions so your provider cache keeps working - Leaves a session alone if it's already cached and cheap Results on my own sessions: - 29 t
Sep 18, 2026X postsView on X
It remembers its decisions to keep provider caching working. It leaves sessions alone if they are already cached and cheap.

Also filed under Agents & browsers

  • Evaluates Tool-Using Agents with Jev in CI

    The project evaluates a real tool-using AI agent using code checks, a calibrated Jev judge, and an LLM judge. It is wired into CI.

  • Watchdog for AI Coding Agents

    Jev Watch is a watchdog for AI coding agents that stops Codex or OpenCode when they loop, stall, or drift off task, then resumes the same session with a correction.

  • Fraud Investigation Agent

    The author is building a fraud investigation agent using Jev and TigerGraph. Its flow goes from an alert through graph evidence, a Bayesian update, a pattern, Jev’s extra lookup, policy, a verdict, and human approval.

  • Coding-Agent Runtime Using Jev Decisions

    Distill is a coding-agent runtime that uses Jev decisions for model routing, context retention, and tool selection.