rhesis
01MCP server Claude CodeCodexCursor +2
MCP server "rhesis", hosted remotely, as configured in rhesis-ai/rhesis.
391 4d ago A
tokens not measured
MCP server Claude CodeCodexCursor +2
MCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF. Runs locally from the @kryptosai/mcp-observatory npm package.
146 6d ago A
tokens not measured
original MIT
resilireplay
03aliengineering-byte/resilireplay
MCP server Claude CodeCodexCursor +2
Inject deterministic MCP failures, verify bounded recovery, and generate executable regression tests. Runs locally from the resilireplay npm package.
2 4d ago A
tokens not measured
original Apache-2.0
evolveguard
04MCP server Claude CodeCodexCursor
Regression-testing CI gate for self-edited Claude Agent Skills (SKILL.md, MEMORY.md): golden-transcript record/replay against a skill's own declared and inferred capability surface, zero hosted infrastructure. Runs locally from the evolveguard-cli Python package.
1 7d ago A
tokens not measured
original MIT
hotato
05MCP server Claude CodeCodexCursor
Find what broke in your agent calls. Pin it and CI stays red until you fix it. Local call forensics and regression guards for AI agents: turn timing, and whether the agent did what it said. Nothing leaves your machine. Runs locally from the hotato Python package.
1 4d ago A
tokens not measured
original MIT
agenttape
06MCP server Claude CodeCodexCursor
MCP server "agenttape" as configured in jiangkoumo/agenttape. Runs ./dist/mcp-server.mjs with node.
1 2d ago A
tokens not measured
original MIT
agent-eval
07MCP server Claude CodeCodexCursor
Statistical regression testing for LLM agents. Get a p-value on whether behavior actually shifted between versions, not just whether one run looked different. Apache 2.0, self-hostable, no SaaS dependency -- a Promptfoo alternative for the statistical testing gap threshold-based eval tools don't cover. Runs locally…
0 7d ago A
tokens not measured
original Apache-2.0
MCP server Claude CodeCodexCursor +2
Vendor-neutral CLI and MCP server that verifies the token and cost savings AI-coding-agent context-reduction proxies (rtk, headroom) actually deliver, measured against a real 23-task labeled corpus with a local tokenizer instead of the proxy's own claimed. Runs locally from the tokentrust-cli npm package.
0 7d ago A
tokens not measured
original Apache-2.0
MCP server Claude CodeCodexCursor +2
agent-regress is a local MCP (Model Context Protocol) server that provides tools for AI coding agents to execute, evaluate, and diff regression tests for LLM agents. It integrates directly into your existing AI coding environment via the Model Context Pro. Runs locally from the agent-regress npm package.
0 1mo ago A
tokens not measured
original MIT
repoimmune
10MCP server Claude CodeCodexCursor +2
MCP server "repoimmune" as configured in Alex0AI/RepoImmune. Runs locally from the repoimmune Python package.
0 12d ago A
tokens not measured
original Apache-2.0
staysfixed
11MCP server Claude CodeCodexCursor +2
Prove that what already worked still works after an agent changed the code. Picture checks, guards for fixed bugs, a pre-release walkthrough, and known-good markers — as a CLI and as an MCP server. Runs locally from the staysfixed npm package.
0 yesterday A
tokens not measured
original MIT