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)
0%+5%88 tracked days
simular-ai/Agent-SNanmiCoder/cc-haha

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.

AxisAgent-Scc-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.

Runs in cli, web-app. Works with byok, openai, anthropic, gemini, other-fixed.

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)
Runs in cli, web-app. Works with anthropic, openai, byok, local-ollama.

What people want from each one

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.