7df-lab/devo

What it solves

Devo provides a model-neutral coding agent that allows developers to maintain control over their model choice, runtime behavior, and workspace execution. It is specifically designed for teams that need to operate outside of a single hosted ecosystem, supporting private, intranet, and air-gapped environments where hosted agent services are not permitted.

How it works

Devo is built as a lightweight Rust runtime that can be interfaced with via a Desktop app or a terminal-based TUI/CLI. It connects to various LLM providers (such as DeepSeek, Qwen, Kimi, and Anthropic) using provider/model bindings. It leverages the Model Context Protocol (MCP) to connect external tools and context, and supports "Agent Skills" for repeatable workflows. To improve code discovery, it includes an optional bundled MCP server for semantic code search using a local CPU embedding model combined with BM25 keyword matching.

Who it’s for

Software engineers and enterprise teams who require a private, flexible coding agent that can run locally or within a private network, and who want the ability to switch between different LLM providers without being locked into one ecosystem.

Highlights

• Model Neutrality: Supports OpenAI-compatible, Anthropic-compatible, and various other model endpoints (DeepSeek, Qwen, Kimi, etc.).
• Dual Interface: Offers both a graphical Desktop app and a terminal-native TUI/CLI.
• Extensibility: Integrates with MCP servers and reusable Agent Skills.
• Enterprise Ready: Supports offline installation and runs as a single local Rust binary for private environments.
• Advanced Agentic Features: Includes a "Plan Mode" for multi-step task breakdown, parallel tool calls, and permissioned tool execution.
• Semantic Search: Built-in optional local semantic code search to reduce context window waste compared to simple grep/find.