Updated

Open-source CLI that measures and improves agent experience: it runs real coding agents against your Skills, CLIs, SDKs, MCP servers or docs in sandboxed sessions, captures where they get stuck, and lets your own coding agent test fixes before you publish.

Pricing Free free to use
Visit site

Follow Gauge to get an email when its listing changes, such as new pricing or features. One digest a day at most, and you can unsubscribe anytime.

Company Gauge
Pricing model Freemium
Paid plans None listed
Category peers 11
01Key features
  1. 01

    Runs Claude Code, Codex, Pi and OpenCode in fresh Docker sessions

  2. 02

    Normalizes agent events into consistent transcripts and structured findings

  3. 03

    Saved evals, preference prompts and shared Markdown cases for CI

  4. 04

    Tests unreleased CLI/SDK tarballs and working-tree Skills before publishing

  5. 05

    Issue tracking with fix, mute, reopen and recheck commands

  6. 06

    `gauge watch` live view of past and running sessions

  7. 07

    Hosted mode adds automatic analysis, authenticated MCP/API and docs testing

02Pricing

Freemium

CLI is free and open-source (MIT) and the local loop needs no Gauge account; agent usage is billed to your own provider or subscription. Hosted Gauge runs on a Gauge workspace with credits.

03Who it's for

Best for

Teams shipping CLIs, SDKs, MCP servers, Skills or docs who want evidence of how coding agents actually use them and a repeatable loop to fix friction.

Not ideal for

Developers looking for a coding assistant to write their own app code, or environments without Docker and Node.js 22.13+.

04Verdict
A distinctive, fast-shipping eval loop for agent-facing products; still early with a small community, and the richer analysis lives in the paid hosted tier.
ai.dosa.dev editorial · Nov 5, 2026
05Recent updates

v0.28.0 (Nov 4, 2026) added hosted `--cli-rules` to stub or redirect CLI commands per run; v0.27.0 (Nov 2) added hosted setup/teardown scripts, issue fix/mute/recheck commands and `gauge watch`.

As of

06Pricing & FAQ
Is Gauge free?

Gauge is Freemium. CLI is free and open-source (MIT) and the local loop needs no Gauge account; agent usage is billed to your own provider or subscription. Hosted Gauge runs on a Gauge workspace with credits. Check the official site for current plans.

Is Gauge open source?

Yes - Gauge is open source. CLI is free and open-source (MIT) and the local loop needs no Gauge account; agent usage is billed to your own provider or subscription. Hosted Gauge runs on a Gauge workspace with credits.

How much does Gauge cost?

CLI is free and open-source (MIT) and the local loop needs no Gauge account; agent usage is billed to your own provider or subscription. Hosted Gauge runs on a Gauge workspace with credits. Pricing changes often - verify on the official site.

Who is Gauge best for?

Teams shipping CLIs, SDKs, MCP servers, Skills or docs who want evidence of how coding agents actually use them and a repeatable loop to fix friction.

Who is Gauge not ideal for?

Developers looking for a coding assistant to write their own app code, or environments without Docker and Node.js 22.13+.

What are the best Gauge alternatives?

The closest Gauge alternatives on ai.dosa.dev are GitAuto, AgentDiff, Agent QA - all listed under AI Testing & Quality Assurance.

Who makes Gauge?

Gauge is developed by Gauge. It is listed in the AI Testing & Quality Assurance category on ai.dosa.dev.

07More in QA & Testing
08Tags
  • agent-experience
  • evals
  • mcp
  • claude-code
  • open-source
Track Gauge in your AI stack

Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.

Compare QA & Testing Sign in to save
Content on this page is AI-generated. Please verify details with the vendor's website for accuracy. Are you the maker? Get your Featured badge ← Back to directory