“Source is public: you can read it before you run it.”

An open-core platform for testing, simulating and monitoring multi-step AI agents in production, including an open-source framework for running adversarial conversation simulations before launch.

“Open source, stated by the project itself.”

A debugging tool that reads Claude Code's own transcripts and turns them into a flight-recorder view showing loops, errors, and token burn, for developers using coding agents, instead of manually digging through raw logs.

“You can see how it works, not just what it promises.”

A CLI that actually runs your test suite before letting an AI coding agent's merge-ready claim through, catching agents that say tests passed when they didn't.

“Source is public: you can read it before you run it.”

A lightweight proxy that sits in front of coding-agent tool calls to block repetitive failing calls, mutate strategy when the agent is stuck, and compress bloated tool outputs, working across Claude, OpenAI, DeepSeek, Ollama, and OpenCode.

“Open source, stated by the project itself.”

An MCP-based JetBrains IDE plugin that gives AI coding agents refactors, inspections, debugging and test-running, so they need fewer manual fixes.

“You can see how it works, not just what it promises.”

Gives AI coding agents pre-built context about a codebase so they spend less time exploring files and history before diving into the actual task.

“Source is public: you can read it before you run it.”

A statusline add-on for Claude Code that shows a sponsored ad while you wait and splits the revenue with you via Stripe; ad targeting runs locally on your device.

“Open source, stated by the project itself.”

Scans code for accidentally leaked secrets like API keys before it's committed, aimed at developers whose AI coding agents generate code fast enough to make mistakes easy to miss.

“You can see how it works, not just what it promises.”

An open-source, Git-native IDE for running and reviewing AI coding agents — shows what changed in the logic, not just the diff. Built for developers working with AI agents.

“Source is public: you can read it before you run it.”

Deploys a frontend or full-stack app to a live shareable link about 15 seconds after you type "deploy" inside Claude Code. Built for developers already coding with Claude Code, free for frontend apps with no sign-up.

“Open source, stated by the project itself.”

An open-source terminal coding agent with full file, command and app access on your machine; you supply your own Claude, GPT or other API key to power it.

“You can see how it works, not just what it promises.”

Runs Claude Code automatically from webhooks or cron jobs, fully self-hosted -- developer infrastructure for automating AI coding tasks, despite the keyword tag claiming no AI is mentioned.