KunAgent/Kun

Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.

What it solves

Kun is a local-first AI agent workbench designed to move AI from simply answering questions to executing real-world work. It solves the fragmentation between planning and execution by providing a unified environment where agents can plan, execute, verify, and deliver software and content projects while keeping evidence of their work tied to the task.

How it works

Kun operates via a shared local runtime (kun serve) that powers both a desktop GUI and a terminal TUI, ensuring continuity across different interfaces. It organizes work into two primary modes:

  • Code Mode: Focused on software delivery, providing project context, file editing, terminal access, Git/Worktree integration, and a Design canvas for prototyping.
  • Work Mode: Focused on content creation, allowing for Markdown editing, PDF/Office document analysis, spreadsheet processing, and presentation generation.

Agents follow a structured workflow: clarifying goals, forming a plan, executing with tool calls and file modifications, and providing evidence (like Diffs or test results) for final delivery.

Who it’s for

It is built for developers and knowledge workers who want an AI agent capable of handling end-to-end tasks within their local environment, supporting a wide variety of LLM providers (including OpenAI, Claude, Gemini, DeepSeek, and local models via Ollama).

Highlights

  • Unified Runtime: Shared state between GUI and TUI for seamless switching between visual and keyboard-centric work.
  • Local-First Architecture: Sessions, preferences, and logs are stored locally by default.
  • Multi-Modal Workflows: Integrated support for both coding (Code mode) and general productivity/writing (Work mode).
  • Extensibility: Supports Scheduled tasks, Loops, Hooks, MCP (Model Context Protocol), and a dedicated extension platform.
  • Provider Agnostic: Compatible with a vast array of cloud and self-hosted model providers.

Related

  • Project
    ApodexAI/FrontierAgent

    FrontierAgent is an open‑source, terminal‑based runtime that lets you run autonomous ReAct agents or parallel Agent‑Team workflows. It provides a sandboxed filesystem, live TUI task board, asynchronous user interventions, and a built‑in benchmark harness for research‑grade long‑horizon tasks. Install with `uv`, point it at any OpenAI‑compatible model endpoint (including the free Apodex‑1.1 service), and run either `--mode react` for a single agent or `--mode agent_team` for coordinated parallel agents. The project is Apache‑2.0 licensed.

  • Project
    QwenLM/qwen-code

    Qwen Code is an open‑source AI coding agent that runs in the terminal, desktop, web, IDEs, and chat apps. It supports multiple LLM providers (OpenAI, Anthropic, Gemini, Qwen, Ollama, vLLM), offers agentic features like auto‑memory, sub‑agents, dynamic workflows, and provides SDKs for TypeScript, Python, and Java. Installation is a one‑line script or npm/Homebrew, and the tool can be used interactively (`qwen`) or headlessly in scripts. Benchmarks on SWE‑bench show ~77 % average pass@3 across versions. The project is Apache‑2.0 licensed and actively maintained.

  • Project
    SeemSeam/claude_codex_bridge

    CCB (Claude‑Codex‑Bridge) is a cross‑platform terminal UI that lets you run many LLM‑backed CLI agents (Codex, Claude, Gemini, etc.) together in visible panes, define collaboration graphs, share a project‑wide memory file, and even control the workspace from an Android app. Install via npm, configure with a built‑in UI, and manage providers, roles, and rich‑media terminals from the command line.

  • Project
    hAcKlyc/MyAgents

    An open-source desktop workspace for personal AI agents that integrates local files, terminals, and a task scheduling system to move beyond simple chat interfaces.

  • Project
    iOfficeAI/AionUi

    AionUi is an open‑source, cross‑platform desktop app that turns LLM APIs into autonomous office assistants. It ships with a built‑in Rust agent (zero‑setup), supports 30+ AI providers, can read/write Word/PPT/Excel files via OfficeCLI, integrates dozens of existing CLI agents, offers team‑mode orchestration, scheduled cron jobs, and remote access through a WebUI or chat‑bot bridges (Telegram, WeChat, etc.). Ideal for developers, analysts, and power‑users who want AI to act on their files and automate tasks without writing glue code.