# NanmiCoder/cc-haha

Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Feishu, DingTalk, Telegram, WhatsApp and H5 access.

Repository: https://github.com/NanmiCoder/cc-haha
Canonical: https://ross.abutalabs.com/products/cc-haha
Language: TypeScript
License: MIT
License Family: permissive
Topics: agent, ai, ai-agent, anthropic, claude, claude-code, coding-agent, computer-use, desktop-app, electron, llm, mcp, react, typescript
Last push: 2026-08-23T18:32:30+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 11
- inputs: {"age_days": 155, "days_push": 10, "days_rel": 11, "gap_med": 2.0, "n_releases_24m": 41}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14232, forks 8543 (observed 2026-08-28T04:11:06.477258+00:00)

## What it is
A local-first cross-platform desktop workspace for Claude Code and AI coding agents, built with Electron, React, and TypeScript. It provides multi-session workspaces, Git worktree launching, diff review, MCP/SubAgent management, multi-model support, Computer Use, a skill marketplace, and IM integrations (WeChat, Feishu, DingTalk, Telegram, WhatsApp).

## Use cases
- manage multiple claude code sessions from a desktop app
- review code diffs from ai coding agents
- run coding agents on git worktrees
- use claude code with chatgpt or grok models
- control agents remotely via telegram or wechat
- manage mcp servers and subagents visually
- schedule automated agent tasks
- monitor agent tool calls and progress

## When to choose
- you use Claude Code or similar coding agents daily and want a GUI instead of the terminal
- you need multi-session, multi-model agent workspaces with diff review
- you want remote access to agents through IM platforms
- you want MCP and SubAgent management in a visual interface

## When to avoid
- you prefer a pure terminal workflow without a desktop app
- you need a headless or CI-based agent runner
- you only need a lightweight CLI wrapper around Claude Code

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, mcp, chat-interface, developer-tools, gui, llm-inference
- domain: developer-tools, large-language-models, desktop-applications
- platform: windows, cross-platform
- tags: claude-code, coding-agent, git-worktrees, computer-use, skill-marketplace, im-integration, desktop-pets, multi-model, ai-agents, automation, macos, linux, electron, desktop

## Member repositories
- NanmiCoder/cc-haha (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:06.477258+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:12:43.015122+00:00, confidence not recorded.
  - readme: https://github.com/NanmiCoder/cc-haha (fetched 2026-08-28T04:11:06.477258+00:00, sha ff2bd90408bb)
- Data as of 2026-08-30T08:39:29.467469+00:00.