A terminal AI coding agent that works across local or cloud models.
# <img width="335" height="89" alt="image" src="https://github.com/user-attachments/assets/833f9e93-c7f6-4a2c-91fd-1285699bcf0b" /> > **[github.com/dxiv/dxa-deimos/](https://github.com/dxiv/dxa-deimos/)** · **[npm `@dxa-deimos/cli`](https://www.npmjs.com/package/@dxa-deimos/cli)** · **[Source @ dxiv/dxa-deimos](https://github.com/dxiv/dxa-deimos)** **Deimos** takes its name from Mars’s outer moon—small, fast, and locked in orbit at the edge of the light. It is a **terminal-native** coding agent: one `deimos` command, **multi-model routing** across pluggable backends (Anthropic, OpenAI-compatible APIs, Gemini, GitHub Models, Ollama, Atomic Chat, and others), a full **tool** surface, **MCP**, slash commands, **agent orchestration**, and streaming sessions built for depth work. This repository ships the **CLI**, a **VS Code extension**, and a **dark terminal theme** forged for long runs in the shell. **Link hub:** **[github.com/dxiv/dxa-deimos/](https://github.com/dxiv/dxa-deimos/)** is the canonical entry—npm, GitHub, and related surfaces in one place. **License & marks:** [MIT](LICENSE). Third-party names and APIs appear only for interoperability and factual description. **[LEGAL.md](LEGAL.md)** sets out attribution, trademarks, and how to report concerns. **Package:** [**@dxa-deimos/cli**](https://www.npmjs.com/package/@dxa-deimos/cli). **Source & issues:** **[github.com/dxiv/dxa-deimos](https://github.com/dxiv/dxa-deimos)**. **Scope:** CLI, documentation, VS Code extension, and CI are maintained as a single product line. **Tree:** `bin/`, `dist/cli.mjs`, `src/`, `vscode-extension/`, `docs/`, optional `python/`, `.github/` workflows, and root policy files—see [Repository structure](#repository-structure). --- [](https://github.com/dxiv/dxa-deimos/actions/workflows/pr-checks.yml) [](https://
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.