agentgauge-harness provides a statistical regression testing framework specifically designed for MCP (Model Context Protocol) tool descriptions. It quantifies whether modifications to tool definitions result in measurable improvements or regressions in agent task success rates. It also includes a deterministic defect linter as a secondary utility. The package is intended for developers building and iterating on AI agents that use tool-calling interfaces.
agentgauge-harness sits in PulseGate's LLM eval & observability category. It focuses on evaluating whether changes to MCP tool descriptions actually improve or regress agent task performance. It is built as an open-source project for AI agent developers. agentgauge-harness is open source under the Apache-2.0 license. The product ships for the command line.
Behind agentgauge-harness is Gaurav Gandhi, and the product first shipped in 2026. Development happens publicly on GitHub with 165 commits in the last 90 days. Key capabilities include Statistical Regression, Task Success Measurement, and Defect Linting. It exposes integrations via an MCP server.
Latest indexed changes and source events
agentgauge-harness verified by the PulseGate indexer
Other apps tracked under the same category.
