opendev-to / opendev

Open-source AI coding agent that spawns parallel agents, each bound to the LLM of your choice. Website and documentation coming soon! --- Introduction OpenDev is an open-source, terminal-native coding agent built as a compound AI system. Instead of a single monolithic LLM, it uses a structured ensemble of agents and workflows — each independently bound to a user-configured model. Work is organized into concurrent sessions composed of specialized sub-agents. Each agent executes typed workflows (Execution, Thinking, Compaction) that independently bind to an LLM, enabling fine-grained cost, latency, and capability trade-offs per workflow. Each workflow is a modular slot you can bind to any LLM of your choice: **Normal** (execution), **Thinking** (reasoning), **Compact** (context summarization), **Self-Critique** (output verification), and **VLM** (vision). For example, use Claude Opus for execution, GPT-o3 for thinking, and a lightweight Qwen model for compaction. Together, these combinations form a compound AI system where multiple models collaborate, each optimized for its role. OpenDev is written in **Rust** for maximum performance and minimal resource usage. Looking for the original Python version? See opendev-py (archived). --- Why OpenDev? • **Proactive, not reactive.** OpenDev can plan, execute, and iterate autonomously. Kick off a refactoring, walk away, and come back to a PR ready for review. • **Multi-provider, multi-model.** Assign different models from different providers to every workflow and session, all running in parallel. Your models, your rules. • **TUI + Web UI.** A full terminal UI for power users and a Web UI for visual monitoring. The Web UI supports remote sessions, so you can start a task from your phone and let OpenDev work while you sleep. • **Fast.** Written in Rust with a ~3.7MB release binary. Instant startup, low memory footprint. --- Installation Quick Start Prefer a guided walkthrough? Run to interactively choose providers, models, and workflow bindings. See the Provider Setup Guide for all 9 supported providers, authentication details, and advanced configuration. Multi-Provider Support OpenDev supports 9 LLM providers: **OpenAI**, **Anthropic**, **Fireworks**, **Google**, **Groq**, **Mistral**, **DeepInfra**, **OpenRouter**, and **Azure OpenAI**. Each provider's models can be independently assigned to 5 workflow slots: • **Normal** -- Primary execution model for coding tasks and tool calls • **Thinking** -- Complex reasoning and planning (falls back to Normal) • **Compact** -- Context summarization when history grows long (falls back to Normal) • **Critique** -- Self-critique of agent reasoning (falls back to Thinking) • **VLM** -- Vision/image processing (falls back to Normal if it supports vision) Mix and match providers per slot in : See the Provider Setup Guide for the full list of env vars, fallback chains, and configuration options. MCP Integration Dynamic tool discovery via the Model Context Protocol for connecting to external tools and data sources. Development Web UI The frontend is a React/Vite app in : Contributing If you're interested in contributing to OpenDev, please open an issue or submit a pull request. --- How OpenDev Compares • **vs. Claude Code / Codex CLI / Gemini CLI:** Closed-source tools that lock you into a single provider. OpenDev is fully open source and lets you mix models from any provider, independently bound per workflow (execution, thinking, critique, compaction, vision). • **vs. OpenCode:** OpenCode is a great open-source coding agent with TUI, Web UI, and LSP support. However, its architecture is not modular enough to support per-workflow model binding, concurrent multi-agent sessions, or compound AI orchestration. • **vs. OpenClaw:** OpenDev and OpenClaw share similar concepts around autonomous AI agents. The key difference is focus: OpenDev is purpose-built for the software development lifecycle, with context engineering, structured agent workflows, and deep code understanding. --- Star History