llm-agentspec
llm-agentspec is an open-source CLI tool that provides pytest-style behavioral contract testing for LLM agent tool-call sequences. It helps developers validate and ensure the reliability of agent workflows by automating behavioral checks.
Overview
4 featuresllm-agentspec is an Agent evaluation & testing project. It focuses on ensuring LLM agent tool-call sequences meet behavioral contracts for reliability and correctness. It is built as an open-source project for AI agent developers and testers. llm-agentspec is open source under the MIT license. It runs on the command line.
llm-agentspec first shipped in 2026. The project is developed in the open on GitHub with 18 commits in the last 90 days. Key capabilities include behavioral contract testing, LLM agent tool-call validation, and pytest-style interface.
Summary written by a language model from the project’s public pages.
- Behavioral contract testing
- LLM agent tool-call validation
- pytest-style interface
- CLI tool
Built with & integrations
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about llm-agentspec
- What does llm-agentspec do?
- Llm-agentspec focuses on ensuring LLM agent tool-call sequences meet behavioral contracts for reliability and correctness. It is catalogued under Agent evaluation & testing on PulseGate.
- Who should use llm-agentspec?
- llm-agentspec is an open-source project built for AI agent developers and testers.
- Is llm-agentspec free?
- Yes — llm-agentspec is open source under the MIT license and free to use.
- What platforms does llm-agentspec run on?
- llm-agentspec runs on the command line.
- Is llm-agentspec still maintained?
- The GitHub repository shows 18 commits in the last 90 days.
- How long has llm-agentspec been around?
- llm-agentspec first shipped in 2026.
- Is llm-agentspec open source?
- Yes — llm-agentspec is open source under the MIT license, developed on GitHub.
Similar projects
Closest matches by what these projects do