why are you wearing that stupid man suit? — a dark factory where AI agents build software autonomously
# bunny <p align="center"> <img src="https://media4.giphy.com/media/v1.Y2lkPTc5MGI3NjExMDZ2N2ZscWE1YTduemtlaHFuZ2RkbXc4cmVkZ3dtNTRkZ2x2d3VhYyZlcD12MV9pbnRlcm5hbF9naWZfYnlfaWQmY3Q9Zw/26vIemlpNzy5CSOli/giphy.gif" alt="frank" width="480"/> <br/> <em>"why are you wearing that stupid man suit?"</em> </p> an autonomous build system for solo developers. two adversarial LLMs (Gemini writes code, Gemini writes tests to break it), one pipeline, and a persistent knowledge graph that compounds across builds. ``` bny hop "add user auth" # spec → plan → test → build bny spike "prototype X" # same thing, guardrails off bny digest docs/ # feed the knowledge graph bny brane ask "question" # query it bny brane storm "topic" # brainstorm against it bny brane tldr # what does it know? ``` auto-initializes on first `bny` command. no explicit setup required. ## how it works gemini writes tests to break things. gemini writes code to survive them. neither sees the other's prompt. ``` bny hop "description" 1. spec gemini specifies, gemini challenges 2. plan gemini plans + generates tasks 3. test 3×3 narrowing — gemini writes tests, gemini implements 4. build implement + verify + retro + ruminate → knowledge graph ``` code ships when gemini beats gemini's tests. then the graph learns. ## prerequisites - [bun](https://bun.sh) >= 1.1.0 - [gemini CLI](https://docs.anthropic.com/en/docs/claude-code) (Anthropic) - [gemini CLI](https://github.com/google-gemini/gemini-cli) (Google) - `ANTHROPIC_API_KEY` and `GEMINI_API_KEY` in your environment ## install from source: ```bash git clone https://github.com/ahoward/bunny.git && cd bunny ./dev/setup ``` or via the install script: ```bash curl -fsSL https://raw.githubusercontent.com/ahoward/bunny/main/install.sh | bash ``` then add bunny's `bin/` to your PATH (or symlink `bin/bny` somewhere in your PATH): ```bash export PATH="$PWD/bin:$PAT
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.