tool-eval
tool-eval is a command-line framework for evaluating the tool usage of AI agents. It provides researchers and developers with tools to analyze and benchmark agent interactions with external tools.
Open SourceMITCLI
Overview
4 featuresIn the LLM eval & observability space, tool-eval takes a focused approach. It enables researchers to evaluate and analyze how AI agents use tools in various scenarios. tool-eval is an open-source project aimed at AI researchers and developers. The project is open source (MIT). It ships for the command line.
It is developed by skwallace36, and it first shipped in 2026. Among its 4 catalogued features are AI agent evaluation, tool use analysis, and CLI interface.
Summary written by a language model from the project’s public pages.
- AI agent evaluation
- Tool use analysis
- CLI interface
- Open source
Tags
agent-evaluationtool-use-analysisai-framework
Built with & integrations
Runs on
CLI
Trust & compliance
License
MIT
Verified signals
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about tool-eval
- What is tool-eval?
- Tool-eval enables researchers to evaluate and analyze how AI agents use tools in various scenarios. It is catalogued under LLM eval & observability on PulseGate.
- Who should use tool-eval?
- tool-eval is an open-source project built for AI researchers and developers.
- Is tool-eval free?
- Yes — tool-eval is open source under the MIT license and free to use.
- What platforms does tool-eval run on?
- tool-eval runs on the command line.
- Is tool-eval still maintained?
- Activity appears to have slowed — PulseGate's most recent liveness signals classify this listing as stale.
- What projects are similar to tool-eval?
- Similar projects tracked by PulseGate include agent-eval, trace-eval, and evalite.agent-evaltrace-evalevalite
- Who makes tool-eval?
- tool-eval is developed by skwallace36.
- When did tool-eval launch?
- tool-eval first shipped in 2026.
Similar projects
Closest matches by what these projects do