|
flowgate — Guardrails for AI coding agents that actually hold
Your AI coding agent deployed before tests and approved before review, and a longer prompt didn't fix it. flowgate puts agents on a state machine they can't...
|
83 % |
|
TestCatalyst — AI Test Management
TestCatalyst generates test cases with AI, runs them through your own agent via MCP, files bugs that close themselves, and streams every run live to a sharea...
|
83 % |
|
Reliqa — Autonomous AI QA Agent
Reliqa is an autonomous AI QA agent that tests web products in a real browser and returns a verified PASS/FAIL report with evidence.
|
83 % |
|
Assevra — Find agent failures before your users do
Open-source agent evaluation with actionable findings, explicit release gates, and portable evidence. Connect captured runs, fix failing cases, and verify th...
|
83 % |
|
OpenReactor
OpenReactor is a self-evolving product engine: request intake, public issues, agent judgment, PRs, and automatic deployment.
|
82 % |
|
Traceback | The autonomous QA suite for software that ships
The autonomous QA suite for web and mobile. Self-healing tests, the Operator, PR testing, MCP, and more.
|
82 % |
|
Opsical — CI/CD testing for AI agents
Opsical is CI/CD testing infrastructure for tool-using AI agents. Simulate adversarial scenarios, catch behavioral regressions, and block unsafe releases bef...
|
82 % |
|
SmoothSDLC Systems - Audit-grade software, at agent speed
SmoothSDLC builds audit-grade software at agent speed, the way regulated teams build: standards written down as rules, work checked against them as it happen...
|
82 % |
|
GetMindZone. Reliability for production AI.
A reliability practice for teams building single-agent and multi-agent systems. Observability, verification, automated testing. The work of making production...
|
82 % |
|
goBIGai — Agentic Workflow Systems
Anirudh Voruganti designs and ships production-grade agentic workflow systems for technical founders and CTOs at funded startups. Custom engagements. Real pr...
|
82 % |
|
dogud — AI agent orchestration that finishes the job
dogud turns plain instructions into coordinated agent workflows — planned, executed, and verified without babysitting.
|
82 % |
|
Chanly
The agent platform that shows you everything. Visual, open, controllable, transparent — built for SMBs and AI startups.
|
82 % |
|
Combat Log | Automatic work visibility
Capture the work once. Generate everything. Combat Log turns your team's activity across GitHub, Jira, Linear, and Trello into weekly briefs, 1:1 prep, relea...
|
82 % |
|
Managed QA Service to Accelerate Your Dev Team — Agent Design Check
Managed QA service for dev teams: recorded, checklist-tracked test sessions with evidence-backed findings delivered to Slack, GitHub, Linear, Jira, or Notion.
|
82 % |
|
FeedFlight — from "a tester complained" to "your agent's on it."
FeedFlight pulls beta feedback out of TestFlight, triages it on one board, and feeds the real bugs straight into your coding agent. The loop from complaint t...
|
82 % |
|
Safe to Merge: Building Reliable Software in the Age of AI Agents
A practical handbook for building reliable software when AI agents write and ship more of the code. Learn how teams are rethinking software engineering, code...
|
82 % |
|
Nemi — Self-evolving test agents
Autonomous testing agents that learn from your codebase, test history, and past failures.
|
82 % |
|
Constolve — find out how your agent fails before your customers do
We put your AI agent through hundreds of tests, run every one more than once, and prove whether a fix actually held.
|
82 % |
|
LightQA: US-Based QA & Custom Test Automation
US-based QA engineer for startups and product teams: custom test automation for web, mobile and desktop, hands-on QA, QA strategy and AI-feature testing. No...
|
81 % |
|
Versalist - Know What Your Agent Does Before You Release It
Versalist helps developers test AI agents, inspect failures, and compare changes before release.
|
81 % |
Detected social media networks