7df-lab/devo

Model-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible / Anthropic-compatible model API. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills,and local code search.

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.

Related

  • Project
    decocms/studio

    deco Studio is an open‑source, TypeScript‑first platform that lets organizations run private AI agents. It provides a single Model Context Protocol (MCP) control plane for routing model calls, managing secure connections to internal tools, handling SSO/RBAC, audit logging and cost attribution. Agents bundle context, tools and policies; connections store encrypted credentials for services like GitHub, Slack or databases; and the model layer is interchangeable (OpenRouter, Anthropic, OpenAI, etc.). The system can be run locally, in Docker, or via Helm on Kubernetes, and includes full observability via OpenTelemetry.

  • Project
    sudoprivacy/sudocode

    Sudo Code is an open‑source, Rust‑based CLI AI coding assistant for terminal‑centric power users. It talks to any LLM provider via the open ACP protocol, runs inline without hijacking the screen, and can be used interactively, as a one‑shot pipe‑friendly command, or as a headless server for editors. Designed for heavy‑user productivity, it emphasizes model‑agnosticism, local‑first operation, file‑based session logs, and a stable, version‑pinned surface.

  • Project
    smallnest/pigo

    A command-line AI coding agent written in Go that can read/write files and execute shell commands to automate software development tasks.

  • Project
    OpenCoworkAI/open-cowork

    Open Cowork is a free, open‑source desktop app that wraps Claude‑style (and other) LLMs into a local AI‑agent workspace. With one‑click installers for Windows/macOS, VM‑level sandboxing (WSL2/Lima), a built‑in “Skills” system for generating PPTX/DOCX/PDF/XLSX files, MCP connectors for browsers/Notion, and remote control via Feishu or Slack, it lets non‑technical users give natural‑language commands that read/write files, automate GUI apps, and produce professional documents—all running locally with optional VM isolation.

  • Project
    OpenBMB/ChatDev

    ChatDev 2.0 (DevAll) is an open‑source, zero‑code platform that lets you design and run multi‑LLM‑agent workflows via a visual web console or a tiny Python SDK. Define agents and their connections in YAML, launch from the browser or code, and use built‑in templates for data viz, 3‑D generation, game dev, research, etc. The backend is FastAPI, the frontend Vue 3, and the project ships Docker/Makefile support, extensible Python tools, and research‑grade orchestrators (Puppeteer, MacNet).