|
AI Agent Coder — Autonomous coding agent for complex tasks
AI Agent Coder plans, writes, tests, and ships code autonomously. Give it a task, review the PR.
|
83 % |
|
AI QA Engineer for Automated Web Testing | ReTibe
An AI agent that reads your codebase, writes real scenarios, runs them on a schedule in three browsers and catches visual regressions before users do.
|
82 % |
|
AI QA Engineer for Automated Web Testing | ReTibe
An AI agent that reads your codebase, writes real scenarios, runs them on a schedule in three browsers and catches visual regressions before users do.
|
82 % |
|
Kandryn — the backlog writes the code back to you
An AI delivery assistant that reads a work item, runs six agents against it — Raptia and Fovea generate, Synthesia ranks, Veria reviews, Aegis scans for secu...
|
82 % |
|
Rescriptum | Native agent IDE
Native agent IDE with control, project context, and BYOK economics. Multi-round agents, treasury, and cloud usage sync.
|
81 % |
|
Req2QA — Requirements to Test Coverage
Req2QA turns your requirements documents into validated test scenarios, a traceability matrix, and optional live test execution — built for teams without a d...
|
81 % |
|
Repohone — Hone your repo for agents
Repohone is a local-first tool for finding friction in coding-agent sessions and turning it into concrete fixes for your repo. Currently in pre-alpha.
|
81 % |
|
novaCTO | Built with AI. Tested against reality.
|
80 % |
|
Codeep — Autonomous AI Coding Agent
Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.
|
80 % |
|
Rulvar - agent workflows that survive the process
Rulvar is an embeddable TypeScript runtime for durable, budget-bounded multi-agent LLM workflows with per-call model routing, replay, typed outcomes, and tests.
|
80 % |
|
RedFlag - AI security scanner for your codebase
RedFlag runs a deep AI security audit across your GitHub repo and returns every vulnerability - ranked by severity, with the exact file, line, and a one-clic...
|
80 % |
|
Agent V: hand off the task, then review the work
Agent V is a desktop coding agent. Write what you want and how you will know it is done; it does the work and shows you every step.
|
80 % |
|
SuperCollective — An agent that watches your agents
Send us your past runs. We learn what a successful execution looks like, find the few that drifted, and explain what changed.
|
80 % |
|
ObserverKit · Error tracking your coding agent can read and fix
Catch every error before your users do. A lightweight SDK, European hosting, and an MCP server so your coding agent can triage issues for you.
|
80 % |
|
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...
|
80 % |
|
XORCISE.AI · evaluate cyber AI agents on real systems
Open-source evaluation for cyber AI agents. Run any agent against a real, contained mission and grade the full evidence of what it did, not just the outcome.
|
80 % |
|
Nightglass — Run coding agent fleets, approve every action
Terminal-first approval engine and supervisor for AI coding agents. Run fleets of Claude Code, Codex, and OpenCode agents with a unified rules engine and aud...
|
80 % |
|
Algo CLI — Verified work. Local control.
A local-first agent runtime for tools, durable context, routed agents, and verified work.
|
80 % |
|
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.
|
80 % |
|
RunVouch: the watchdog for unattended AI agents
Proof your scheduled AI agents did the job, and an alert the moment they don't, or start spending. Claude Code Routines, headless claude -p, OpenClaw, n8n, c...
|
80 % |
Detected social media networks