cc-haha vs GenericAgent
The two are close in size: 14.3k stars for cc-haha, 14.1k for GenericAgent. Over the days we have tracked them cc-haha moved +5.3% and GenericAgent +11.8%, so GenericAgent is growing faster right now.
They split the axes: cc-haha leads on customization, GenericAgent on context depth and setup ease.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
A desktop-first, local-first Claude Code workstation that combines worktree-aware code diffs, Computer Use desktop control, H5 remote access and IM integrations in one app.
- Stars
- 14.3k
- Tracked growth
- +5.3%
- Maturity
- ●●●●●
- Last commit
- 3d ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Requires configuring your model provider API key (third‑party billing applies)
Self-evolving agent that crystallizes each solved task into a persistent, reusable personal skill tree from a minimal (~3K-line) seed.
- Stars
- 14.1k
- Tracked growth
- +11.8%
- Maturity
- ●●●●●
- Last commit
- 2d ago
- Language
- Python
- License
- MIT
- Cost to run
- Your LLM API key; provider charges apply
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | cc-haha | GenericAgent |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Diff + Worktree | ●●●●● Whole-repo analysis |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Approval gating | ●●●●● Human-in-the-loop |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Plugins & per-project | ●●●●● Config & prompts |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Cloud API key |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● BYOK + local models | ●●●●● Bring-your-own-key |
Setup ease What it takes to get a first useful run out of it. | ●●●●● API key & config | ●●●●● One-line installer |
Which one to pick
Pick cc-haha if…
Local-first — pick this when you want a desktop agent that runs against your repo/worktree with built-in diffing, permission approvals, extensible skills and multi-provider model support.
- Customization: Plugins & per-project (5/5 against 3/5)
Pick GenericAgent if…
Self-evolving — pick this when you want an agent that autonomously builds reusable skills and gains system-level desktop/browser control over time.
- Context depth: Whole-repo analysis (5/5 against 3/5)
- Setup ease: One-line installer (5/5 against 3/5)
What people want from each one
NanmiCoder/cc-haha
lsdefine/GenericAgent
Questions people ask
Is cc-haha better than GenericAgent?
They split the axes: cc-haha leads on customization, GenericAgent on context depth and setup ease. cc-haha is worth picking when local-first — pick this when you want a desktop agent that runs against your repo/worktree with built-in diffing, permission approvals, extensible skills and multi-provider model support.
Which of cc-haha and GenericAgent keeps my code private?
cc-haha: Self-hostable (4/5). GenericAgent: Cloud API key (3/5).
What does each one cost to run?
cc-haha: Requires configuring your model provider API key (third‑party billing applies). GenericAgent: Your LLM API key; provider charges apply.
Full profiles: NanmiCoder/cc-haha and lsdefine/GenericAgent. Everything else in Computer use.