“Testing”

Autonomous pentesting platform that runs real attack techniques against production environments and re-tests fixes.

Autonomous security testing that attacks applications and reports only findings it has exploited, with a working exploit for each.

Terminal coding agent that routes each development task to Claude, GPT or Gemini based on configurable rules.

Open-source autonomous pentesting agents that run your app, find vulnerabilities and validate them with working proofs of concept.

Terminal coding agent, forked from OpenAI's Codex, tuned for low-cost open models and compatible with ACP editors

Python performance optimizer that uses LLMs to generate, test and benchmark optimizations and opens pull requests.

Sandbox marketplace where AI agents hire AI agents for verified outcomes.

Bootlace AI SpendMap is a free-trial / stress-test JSON meter for AI agent fleet spend.

Builds, previews, QA-tests and publishes web apps from a prompt.

Paid on verified proof: open milestones with test money held on Solana devnet until the proof passes, released only when a referee verifies the work.

Agentic search engine for AI agents: an index of websites verified usable by agents — every capability probed and tested live, tier 1–3 (declared ·…

Ask AgentDrives whether an AI agent can really use a software product, from our agent's real test drives: search the directory, get one product's listing, or…

Augment's Cosmos platform runs agent loops for code review, ticket-to-PR, vulnerability fixes and incident response, with a CLI and IDE plugins

The independent trust layer for AI agents — each agent hands-on tested for one evidence-backed Laddoo Score (0-100).

AWS's spec-driven coding agent that turns prompts into requirements, designs and tasks, available in IDE, CLI, web and mobile

Turn your OpenAPI description into reference docs, an MCP server, SDKs and tests, kept current on every pull request.

Replit's chat-driven agent that builds, tests and deploys apps and can create other agents and automations

Agent that turns a goal in plain words into planned, built and tested work, reachable from Slack and Telegram

Google's asynchronous coding agent that clones your GitHub repo into a cloud VM, plans changes and opens a pull request

Autonomous penetration testing agent with a Kali Docker sandbox, a Textual TUI and any OpenAI-compatible model gateway

Augment's terminal coding agent that edits code and runs tools interactively or in scripts and CI

Self-hosted autonomous pentesting agent that finds and exploits vulnerabilities and logs the command and output for each one

Autonomous security-testing agent on the Pi SDK that plans tasks in a graph and keeps evidence for each conclusion.

Local-first MIT coding agent with DeepSeek defaults, provider switching, OS sandboxing and a checkpoint for every patch.