Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
evalview-mcp
MCP serversRegression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
evalview@0.6.0 -
lastest
MCP serversRun visual regression tests, review diffs, and manage baselines on a Lastest instance.
@lastest/mcp-server@0.3.7 -
SnapVisor
MCP serversVisual regression testing over MCP: upload screenshots, review diffs, approve. No CI needed.
-
agent-eval
MCP serversStatistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
agent-regress-cli@0.1.8 -
edgegate-mcp
MCP serversRegression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI.
edgegate-mcp@0.19.0 -
Curbi
MCP serversCheck agent replies, lint policies, export regression tests and verify caller-trusted proof bundles.
-
mcp-assert
MCP serversThe testing standard for MCP servers. Lint (14 rules), test, and fuzz over real stdio/SSE/HTTP transport. 18 assertion types in YAML. Found 4,794 schema issues across 55 servers. Any language, no mocks, single binary.
git clone https://github.com/blackwell-systems/mcp-assert.git -
agentic-qa-boilerplate
SkillsAgentic QA boilerplate built on Playwright + KATA + TypeScript. Multi-agent skills following the agentskills.io spec, orchestrating the full QA lifecycle: shift-left planning, in-sprint testing, TMS documentation with ROI scoring, KATA automation, and regression with GO/NO-GO. Works across Claude Code, Opencode, etc.
git clone https://github.com/upex-galaxy/agentic-qa-boilerplate.git -
Tracely-ai
AI repositoriesTrace-native CI/CD for AI agents — production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.
git clone https://github.com/Jwuthri/Tracely-ai.git -
hermes-jailbench
SkillsZero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench
git clone https://github.com/hermes-labs-ai/hermes-jailbench.git -
invaris-agentsec
MCP serversAdversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression testing and reports.
git clone https://github.com/invarislabs/invaris-agentsec.git -
What's in this version: 1. Compare two screenshots for layout differences 2. Compare a full screenshot test of browsers to a single baseline browser for layout differences. 3. Compare a screenshot test version to another test version - good for regression tests. 4. Get links to the Comparison UI for visual representation of layout differences
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.