About JarvisCodex

Privacy-first AI coding, no cloud lock-in.

Our Mission

JarvisCodex exists to give developers the power of AI coding assistants without surrendering their code, their data, or their choice of model. We believe the best AI tools should run locally, respect your privacy, and let you bring your own API keys.

What We Build

JarvisCodex is a desktop IDE with an embedded multi-agent runtime. It connects to any LLM provider — OpenAI, Anthropic, Google, Mistral, or local models via Ollama — through your own API keys (BYOK). Your code never touches our servers.

  • Multi-agent orchestration with planner, executor, and reviewer agents
  • Local-first architecture — works fully offline with Ollama
  • Built-in terminal, file tree, and Monaco editor
  • Checkpoint system for safe rollback of AI-generated changes
  • MCP (Model Context Protocol) server support

Technology

Built with Electron, React, TypeScript, and Vite. The agent runtime is a standalone TypeScript package that handles planning, tool routing, staged execution, and result compression. We use SQLite for local persistence and Stripe for billing.

Open Development

We develop in the open on GitHub. Feature requests, bug reports, and contributions are welcome.

Contact

Have questions or want to partner with us?