|
Vizra Evals — Agent Evals for the Laravel AI SDK, Written in Pest
Built for the official Laravel AI SDK: write agent evals as Pest tests, record every run — scores, judge reasoning, cost — and fail CI on regressions instead...
|
83 % |
|
Visual Regression Testing for AI Agents & CI
Visual regression testing as an API. Drop it into CI, drive it from your agent, or let it crawl on a schedule. Catches what your deploys didn't: third-party...
|
82 % |
|
Veval — LLM Regression Testing
Veval captures real production traces and turns them into a regression baseline. When your prompt changes, know what broke before your users do.
|
82 % |
|
EvalDog — catch LLM regressions before your users do
Hosted prompt & RAG evaluation. Upload your test cases, get a graded pass/fail report in seconds. Plus a zero-token CLI for CI and AI agents.
|
82 % |
|
Retrio
Test any AI agent API in under 2 minutes. Catch behavioral regressions and semantic drift with zero SDKs to install and no code instrumentation.
|
82 % |
|
RedCrown | AI regression checks and release evidence
Check AI changes against defined requirements, inspect failures, and review the evidence behind the result. Start with a supported example or your own outputs.
|
81 % |
|
Taso · Test every agent change before production
Compare model, prompt, tool, and MCP changes in repeatable agent evaluations. Inspect release evidence and preview Auto-Eval: production traces into team-rev...
|
81 % |
|
Instryx — Agent Evaluation & Observability for AI Teams
Instryx evaluates AI agents across 100+ dimensions, traces every step, and pinpoints why an agent failed — so teams catch regressions before customers do.
|
81 % |
|
Know when your AI gets worse, before your users do | EvalCore
EvalCore is snapshot testing for AI behavior. Record how your LLM app or agent behaves, then replay it in CI on every change: offline, deterministic, $0.
|
81 % |
|
EvaluatAI — Evaluate your AI Agents in real-time.
EvaluatAI is the continuous testing and evaluation platform for your LLM applications. Move beyond anecdotal checks and implement rigorous, automated testing.
|
81 % |
|
Redwick Labs | AI Agent Red-Teaming Suite
Practical AI agent red-teaming tooling for structured adversarial testing, CI/CD regression workflows, guardrail evaluation, and security reporting.
|
81 % |
|
Quantiles | Local-First AI Evaluation
Local-first AI evaluation for developers and agents. Run, analyze, and compare reproducible evals across models, prompts, benchmarks, and agentic workflows.
|
80 % |
|
AgentProbe — AI Debugging Tool for GitHub Copilot & AI Agents
AgentProbe is the AI debugging tool that gives GitHub Copilot and AI coding agents 25 MCP tools to trace variables, validate hypotheses, and safety-check fix...
|
80 % |
|
EvalFox — Know exactly how good your agent is, all the time
Continuous evaluation for chat-based AI agents. Catch regressions, score quality, and ship with confidence.
|
80 % |
|
Switch LLM models safely — migration testing for AI agents | EvalShift
Switch LLM models or providers without guessing whether your agent will break. EvalShift replays real agent traces on your current model and the one you're s...
|
80 % |
|
Mathew Stevens — Full-Stack Software Engineer
Full-stack software engineer building live products, AI systems, backend APIs, real-time systems, SDKs, developer tools, and mobile apps. SolPulse · Agentic...
|
80 % |
|
Mathew Stevens — Full-Stack Software Engineer
Full-stack software engineer building live products, AI systems, backend APIs, real-time systems, SDKs, developer tools, and mobile apps. SolPulse · Agentic...
|
80 % |
|
QAMind AI — The spec goes in. The proof comes out.
QAMind AI turns requirement docs and browser recordings into structured test cases, Playwright & Selenium scripts, tracked runs and filed bugs — one workspac...
|
80 % |
|
DProvenanceKit — On-device provenance & signed attestation for Swift AI
Turn every AI run into a queryable, diffable, cryptographically signed trace. Catch the silent regressions on-device AI ships — a dropped tool call, a skippe...
|
80 % |
|
ShipsWith — can AI agents actually use your product?
Continuous, sandboxed testing of whether Claude Code, Codex, and Gemini can discover, install, configure, and use your product — with regression alerts on ev...
|
80 % |
Detected social media networks