Open-source, terminal-native AI coding agent with multi-provider support, structured diffs, and persistent memory
# ClawCode CLI CLI coding agent (**ClawCode**) that uses **Azure OpenAI**, **Groq**, or **Google Gemini** to plan and apply code changes. It scans your project (respecting `.gitignore`), sends minimal context to the LLM, and applies structured patches with backups and confirmation. Persistent memory (global + per-project session) survives restarts and model switches. - **Website:** [https://clawcode.vercel.app/](https://clawcode.vercel.app/) - **Documentation:** [https://clawcode.vercel.app/docs](https://clawcode.vercel.app/docs) ## Requirements - **Node.js** >= 18 - At least one AI provider configured (Azure OpenAI, Groq, or Google Gemini) --- ## Installation Install into user space (no `sudo`, no global npm). Requires Node.js >= 18. **macOS / Linux:** ```bash curl -fsSL https://raw.githubusercontent.com/sarhan44/clawcode/main/install.sh | bash ``` **Windows (PowerShell):** ```powershell iwr https://raw.githubusercontent.com/sarhan44/clawcode/main/install.ps1 -useb | iex ``` Then run: ```bash clawcode ``` On first run, ClawCode will guide you through configuring an AI provider. You can also run `clawcode config` any time to add/update providers. <img width="1906" height="824" alt="image" src="https://github.com/user-attachments/assets/be90d8ea-5630-435d-ba77-778b41b3071d" /> *ClawCode interactive UI: logo, project/provider info, activity feed, status bar, and task input.* --- ## Commands | Command | Description | |--------|-------------| | `clawcode` | Open the interactive TUI (default). Select project and provider, then enter tasks. | | `clawcode config` | Add or update AI provider credentials (API keys, endpoints). | | `clawcode shell` | Start REPL mode with `clawcode>` prompt. Use `:exit`, `:provider`, `:project`, `:help`. | | `clawcode "task"` | Run a single task in the current directory (no TUI). | | `clawcode --dir <path> "task"` | Run a task in the specified project directory. | ### Options | Option | Description | |--------|----------
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.