Skip to content
Back to the index

agent-belt

github.comInfrastructure

PulseGate's liveness check found it on 9 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 15 Jun 2026. How this is checked

Evaluation harness for real headless CLI agents - reproducible multi-turn scenarios, rule + LLM scoring, cross-agent comparison

Inferred · not functionally tested

Open SourceApache-2.0WebCLI
agent-belt preview
Visit github.com
16stars
1fork
4features
2026since

Overview

4 features

Purpose: Benchmarking and evaluating headless CLI agents in reproducible scenarios.

Inferred · not functionally tested

Audience: AI agent developers and researchers

Inferred · not functionally tested

Functions: analytics, monitoring

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: unknown

Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: browser, cli

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: github.com. These links do not verify the individual claims.

agent-belt sits in PulseGate's Agent evaluation & testing category. Inferred · not functionally tested: It focuses on benchmarking and evaluating headless CLI agents in reproducible scenarios. Inferred · not functionally tested: It is built as an open-source project for AI agent developers and researchers. Basis unknown · not verified: agent-belt is open source under the Apache-2.0 license. Basis unknown · not verified: It ships for the web and the command line.

It is developed by jfrog, and it first shipped in 2026. The project is developed in the open on GitHub with 16 stars and 8 commits in the last 90 days. Inferred · not functionally tested: Among its 4 catalogued features are agent benchmarking, multi-turn scenario evaluation, and rule and LLM scoring.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Agent benchmarking
  • Multi-turn scenario evaluation
  • Rule and LLM scoring
  • Cross-agent comparison

Topics: Inferred · not functionally tested

Tags
agent-benchmarkingcli-evaluationllm-testing

JSON profile · Text profile · Access guide

Built with & integrations

Runs on
BrowserCLI

Trust & compliance

License
Apache-2.0
Public signals
HTTPSOpen SourceFree tierGitHub · ★ 16Active maintenance

Indexing history

What PulseGate has recorded for this listing

Nothing recorded for this listing in this window.

Frequently asked questions about agent-belt

What does agent-belt do?
Inferred · not functionally tested: Agent-belt focuses on benchmarking and evaluating headless CLI agents in reproducible scenarios. It is catalogued under Agent evaluation & testing on PulseGate.
Who should use agent-belt?
Inferred · not functionally tested: agent-belt is an open-source project built for AI agent developers and researchers.
Does agent-belt have a free plan?
Basis unknown · not verified: Yes — agent-belt is open source under the Apache-2.0 license and free to use.
What platforms does agent-belt run on?
Basis unknown · not verified: agent-belt runs on the web and the command line.
Is agent-belt still maintained?
PulseGate's liveness check found it on 9 Oct 2026. Its GitHub repository shows 8 commits in the last 90 days.
What are alternatives to agent-belt?
Similar projects tracked by PulseGate include agentkit-cli, agentbench-cli, and agentanvil.agentkit-cliagentbench-cliagentanvil
Who develops agent-belt?
agent-belt is developed by jfrog.
When did agent-belt launch?
agent-belt first shipped in 2026.

Similar projects

Closest matches by what these projects do