Show HN: Jevpipe – a fast System 1 for AI agents, as a Unix pipe

Give your coding agent a System 1.

Fast, cheap judgments over thousands of files, lines or records in one shell command,

so your agent decides at scale instead of reading everything itself.

Quick start · Example · Use cases · Measured · Cost

uv tool install jevpipe                             # the CLI
jevpipe auth set-key                                # your OpenRouter key, kept in the system keychain
npx skills add fabianboth/jevpipe --skill jevpipe   # teaches your agent when and how to use it

You need an OpenRouter API key. Where there is no keychain, as in containers, CI or headless Linux, set OPENROUTER_API_KEY instead; it also takes precedence. No uv yet? Install it or use pipx.

Without uv, or with the GitHub CLI #

pipx install jevpipe                                # instead of uv
gh skill install fabianboth/jevpipe jevpipe         # the skill, with the GitHub CLI

Which of the 19 commits in ripgrep 15.1 are new features? Ask each commit message:

git log --format=%s 15.0.0..15.1.0 | jevpipe filter "Is this a new feature?"
ignore/types: add `ssa` type
printer: add Cursor hyperlink alias

jevpipe: 19 records, 2 kept, 0 skipped, 0 failed, $0.000225, 1.1s

Typed answers with map: sort every commit into feature, fix, docs or internal #

git log --format=%s 15.0.0..15.1.0 | jevpipe map -q '{
  "kind": {
    "type": "choice",
    "instructions": "What kind of change is this, for the release notes?",
    "criteria": {
      "feature": "a new capability for users",
      "fix": "a bug fix users would notice",
      "docs": "documentation only",
      "internal": "refactoring, tests, CI, dependencies or release chores"
    }
  }
}'

Every commit becomes one JSON line. One of the 19:

{
  "record": "printer: add Cursor hyperlink alias",
  "answers": {
    "kind": {
      "type": "choice",
      "choice": "feature",
      "probabilities": {"docs": 0.05, "feature": 0.87, "fix": 0.03, "internal": 0.05},
      "confidence": 0.82
    }
  }
}

All 19 took 1.1 seconds and cost $0.0003. Pick from them with jq, for example the fixes: jq -r 'select(.answers.kind.choice == "fix") | .record'. A low confidence marks an answer worth a second look.

Each item is judged on its own, so ask what the item itself can answer:

Classification. Jev against general LLMs on intent routing and prompt-injection detection, from an independent study:

Code search. jevpipe in an agent's hands: 470 searches from the extended CodeSearchNet Challenge in five languages, each over every function of its language.

Read the full benchmark: every language, speed and cost, and the searches where jevpipe loses.

Both read their input like grep: lines through a pipe or from the files you name. With --read-files, each line is a path, and the file it names is judged instead:

git log --format=%s | jevpipe filter "Is this a new feature?"                       # each commit message
jevpipe filter "Is this an error worth a closer look?" app.log                      # each line of app.log
git ls-files | jevpipe filter "Does this file retry failed requests?" --read-files  # each file

jevpipe <command> --help has the rest.

Every record is one request billed to your OpenRouter credit, and the cost follows the size of each record: about a cent per 1,000 commit messages, 4 to 18 cents per 1,000 source files. Asking several questions at once barely changes it. Up to 100 records run at the same time, so hundreds take seconds.

--max-cost 0.50 stops sending requests once the run has spent $0.50; it then exits with status 3 and names the line to resume from. To cap every run by default, run jevpipe config set max-cost 0.50 once; jevpipe config --help lists the other defaults you can set.

Apache-2.0. jevpipe is an independent project, not affiliated with or endorsed by TypeSafe AI; the answers come from Jev, TypeSafe AI's calibrated decision model, through OpenRouter. Building from source needs Rust (rustup picks the pinned toolchain) and PowerShell 7 for ./check.ps1.