Agent-S vs cc-haha
The two are close in size: 12.2k stars for Agent-S, 14.3k for cc-haha. Over the days we have tracked them Agent-S moved +3.9% and cc-haha +5.3%, so cc-haha is growing faster right now.
cc-haha leads on context depth and customization. Agent-S does not take any axis by a clear margin.
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
An open-source, research-backed GUI agent framework that combines grounding models and optional local code execution and achieves SOTA (surpassing human performance on OSWorld).
- Stars
- 12.2k
- Tracked growth
- +3.9%
- Maturity
- ●●●●●
- Last commit
- 35d ago
- Language
- Python
- License
- Apache-2.0
- Cost to run
- Your API keys (provider-dependent)
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)
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 | Agent-S | cc-haha |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Single-screen context | ●●●●● Diff + Worktree |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Basic filters | ●●●●● Approval gating |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Configurable params | ●●●●● Plugins & per-project |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Cloud APIs (your key) | ●●●●● Self-hostable |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-own key | ●●●●● BYOK + local models |
Setup ease What it takes to get a first useful run out of it. | ●●●●● Config + API key | ●●●●● API key & config |
Which one to pick
Pick Agent-S if…
SOTA performance — pick Agent S when you need a research-grade, open-source GUI agent with grounding-model support and optional local code execution.
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.
- Context depth: Diff + Worktree (3/5 against 1/5)
- Customization: Plugins & per-project (5/5 against 3/5)
What people want from each one
simular-ai/Agent-S
Hacker News: Show HN: Agent S: an open agentic framework that uses computers drew 2 points and 1 comments.
NanmiCoder/cc-haha
Questions people ask
Is Agent-S better than cc-haha?
cc-haha leads on context depth and customization. Agent-S does not take any axis by a clear margin. Agent-S is worth picking when sOTA performance — pick Agent S when you need a research-grade, open-source GUI agent with grounding-model support and optional local code execution.
Which of Agent-S and cc-haha keeps my code private?
Agent-S: Cloud APIs (your key) (3/5). cc-haha: Self-hostable (4/5).
What does each one cost to run?
Agent-S: Your API keys (provider-dependent). cc-haha: Requires configuring your model provider API key (third‑party billing applies).
Full profiles: simular-ai/Agent-S and NanmiCoder/cc-haha. Everything else in Computer use.