evalview
hidai25/eval-viewPlugin
Behavior regression testing for AI agents. EvalView detects when your agent's behavior drifts e.g changed tool calls, different outputs, or degraded quality even when traditional tests still pass. Snapshot baselines, check for regressions, and auto-heal flaky results, all from inside Claude Code.
Why this score
Popularity score: 71/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 22, 2026 at commit afbc7f6c715d, first 300 source files (it's a large repo), with Cisco's open-source skill-scanner.
What its code does:
- Reads environment variables and sends network requests with them API clients do this to send your key to the service. Check which service it talks to.evalview/commands/init_cmd.py and 2 more
- Runs shell commands Common for dev tools. Read the commands it runs.dogfood/agent.py:74, evalview/chat.py:479, evalview/openclaw.py:107 and 1 more
- Makes network requestsevalview/commands/_init_tests.py:66, evalview/commands/capture_cmd.py:321, evalview/commands/gym_cmd.py:135 and 6 more
- Reads environment variables, where API keys usually liveevalview/adapters/aider_adapter.py:207, evalview/adapters/goose_adapter.py:210, evalview/skills/adapters/base.py:460 and 1 more
- Installs system packagesscripts/install.sh:42
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Nothing from another maker does quite the same job yet.