The open-source behavior regression gate for AI agents. Think Playwright, but for tool-calling and multi-turn AI agents. Your agent can still return and be wrong. A model or provider update can change tool choice, skip a clarification, or degrade output quality without changing your code or breaking
| Stars | 114 |
| Forks | 20 |
| Language | Python |
| Category | MCP 服务器 |
| License | Apache-2.0 |
| Quality Score | 54.178/100 |
| Open Issues | 6 |
| Last Updated | 2026-06-15 |
| Created | 2025-11-17 |
| Platforms | cli, mcp, python |
| Est. Tokens | ~24k |
Explore other popular mcp 服务器 tools:
eval-view is Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewAI, OpenAI, Anthropic.. It is categorized as a MCP 服务器 with 114 GitHub stars.
eval-view is primarily written in Python. It covers topics such as agent-benchmark, agent-evaluation, agentic-ai.
You can find installation instructions and usage details in the eval-view GitHub repository at github.com/hidai25/eval-view. The project has 114 stars and 20 forks, indicating an active community.
eval-view is released under the Apache-2.0 license, making it free to use and modify according to the license terms.