NanmiCoder/cc-haha

本地优先的跨平台 Claude Code / AI Agent 桌面工作台：多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物；支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git worktrees, diffs, skills marketplace, multi-model, Computer Use, task-aware desktop pets; remote via WeChat, Feishu, DingTalk, Telegram, WhatsApp & H5.

cc‑haha – Desktop Workbench for Claude Code and Other LLMs

What it is

  • A cross‑platform (macOS, Windows, Linux) desktop application built with Electron + React that lets you chat with large language models (Claude, ChatGPT, Grok, etc.) and use them as coding assistants.
  • It bundles a rich UI for multi‑session management, code diff review, built‑in browser preview, image generation, and “Computer Use” – the ability for an agent to control other desktop apps without taking over your real mouse/keyboard.

Key capabilities

Feature What it does
Multi‑session workbench Tabs, project switching, terminal entry, and history all in one pane.
Global search Cmd+K searches across every conversation.
Git branch / worktree launch Start a new session on a specific repo branch or isolated worktree.
Diff review Shows syntax‑highlighted diffs per file, with one‑click revert.
Built‑in browser preview Renders pages the agent just edited, preserving cookies & login state.
Permission modes Five levels from “ask each time” to “skip”, gating dangerous commands and tool calls.
Model picker Connect to Claude, ChatGPT, Grok, DeepSeek, Kimi, GLM, local Ollama/LM Studio models, etc.
Image generation Generate/edit images inside a chat using any OpenAI‑compatible Images API.
MCP server management Graphical UI to add/remove MCP servers (STDIO, HTTP, SSE) with private/shared scopes.
Skill marketplace Browse, preview, and install third‑party skills from ClawHub / SkillHub.
Sub‑Agent visual editor Create and tune child agents, choose model, tools, and permission mode.
Agent Teams workbench Visual collaboration board for multiple agents, showing members, tasks, message flow, and dependencies.
Dynamic workflow orchestration Write and run scripts that schedule sub‑agents, with pipeline, breakpoints, and visual stage view.
Request tracing Local log of each model call with status, latency, and searchable history.
Computer Use (macOS) Agents can take screenshots, click, type, and control other apps without hijacking your real input devices.
Desktop pets Optional animated mascots that react to task status.
H5 remote access Scan a QR code to view the current session on a phone browser.
IM integration Connect Telegram, Feishu, WeChat, DingTalk, WhatsApp, Enterprise WeChat, QQ, Slack for remote chatting and approvals.
Scheduled tasks & usage stats Run jobs on a timer and see local token‑usage trends.

Tech stack

  • Language: TypeScript
  • Desktop: Electron
  • UI: React + Vite
  • Runtime: Bun (for the CLI)
  • CLI UI: React + Ink, Commander.js
  • Model API: Anthropic SDK (plus generic OpenAI‑compatible endpoints)
  • Protocols: MCP, LSP

Getting started

  1. Download the binary for your OS from the Releases page.
  2. Launch the app, open Settings, and add your model provider(s) – API key, endpoint, and default model.
  3. Create a new session, pick a repo/branch if you like, and start chatting.
  4. Optional: run the CLI version (bun install && ./bin/claude-haha) for deeper debugging or custom extensions.

Documentation & community

  • Full docs site: https://cchaha.ai
  • Quick‑start guides: install, connect models, run first session.
  • Detailed sections on Computer Use, workflow, agent teams, IM integration, etc.
  • Community: WeChat enterprise group (QR code in README) and GitHub Issues for support.

License

  • cc‑haha Community Source License 1.0 – free for personal non‑commercial use and internal corporate use. Commercial resale, paid services, or derivative distribution requires a written commercial license.

Who might benefit?

  • Developers who want an all‑in‑one desktop UI for LLM‑powered coding assistance.
  • Teams building multi‑agent workflows or needing remote IM‑based control of agents.
  • Power users on macOS who want “Computer Use” without giving the model direct control of their mouse/keyboard.

This summary is based solely on the repository’s README.

Related

  • Project
    openkursar/hello-halo

    Halo AI Workstation is an open‑source desktop app that combines a chat‑style AI workbench with autonomous “Digital Humans”—AI agents that can run on schedules, keep memory, and collaborate in distributed teams. It supports multiple LLM back‑ends (Claude, ChatGPT, etc.), offers built‑in document editing, web browsing, terminal control, and integrates with IM platforms (Feishu, WeChat, WeCom) for remote hand‑offs. The software runs locally on macOS, Windows, Linux, and has mobile remote clients, requiring no backend service.

  • Project
    lahfir/agent-desktop

    agent-desktop is a cross‑platform CLI and C library that lets AI agents read the desktop UI via accessibility trees and control apps (click, type, window management, etc.) using JSON references.

  • Project
    Prorise-cool/Claude-Code-Multi-Agent

    Claude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`. Key points: - Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`. - Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates. - Skills are defined by `SKILL.md` files and are auto‑discovered. - Works entirely locally (no external API), integrates with Git, and is MIT‑licensed. Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.

  • Project
    wuxiran/cc-pane

    CC‑Panes is an open‑source desktop app (Windows/macOS/Linux) that lets you run, organise and coordinate multiple AI‑coding CLI agents in parallel. It provides workspace‑level dashboards, reusable launch profiles, an MCP‑based orchestration layer, integrated terminal splits, Git/history tools, planning surfaces, and web/Android access—all built with Tauri, xterm.js and Rust.

  • Project
    deepagent-ltd/deepagent-code

    DeepAgent Code (DAC) is a desktop‑plus‑terminal workspace that lets you use an LLM as a coding assistant for multi‑step tasks. It offers persistent sessions, inspectable project memory, sub‑agents for independent jobs, a managed browser, and optional instant‑messaging integration, all configurable with any compatible LLM provider. Licensed under AGPL‑3.0.