Agent-S vs artemis
The two are close in size: 12.7k stars for Agent-S, 13.1k for artemis. Over the days we have tracked them Agent-S moved +5.1% and artemis +975.3%, so artemis is growing faster right now.
They split the axes: Agent-S leads on model freedom, artemis on context depth and noise control and customization 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
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
- 12.7k
- Tracked growth
- +5.1%
- Maturity
- ●●●●●
- Last commit
- 11d ago
- Language
- Python
- License
- Apache-2.0
- Cost to run
- Your API keys (provider-dependent)
Provides a native MCP server that lets AI IDE assistants drive real Android devices with multimodal targeting, safety nets, and replayable diagnostics.
- Stars
- 13.1k
- Tracked growth
- +975.3%
- Maturity
- ●●●●●
- Last commit
- 18d ago
- Language
- Python
- License
- Apache-2.0
- Cost to run
- Self-hosted runtime; model usage may incur cloud API costs
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 | artemis |
|---|---|---|
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 + related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Basic filters | ●●●●● Pre-exec Safety Net |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Configurable params | ●●●●● Custom rules & profiles |
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 | ●●●●● Multiple providers |
Setup ease What it takes to get a first useful run out of it. | ●●●●● Config + API key | ●●●●● One-click start |
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.
- Model freedom: Bring-your-own key (5/5 against 3/5)
Pick artemis if…
Easy setup — one-click local server and native MCP IDE integrations to run reliable, safety-gated automation on real Android devices with rich diagnostics.
- Context depth: Diff + related files (3/5 against 1/5)
- Noise control: Pre-exec Safety Net (5/5 against 3/5)
- Customization: Custom rules & profiles (5/5 against 3/5)
- Setup ease: One-click start (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.
google/artemis
Questions people ask
Is Agent-S better than artemis?
They split the axes: Agent-S leads on model freedom, artemis on context depth and noise control and customization and setup ease. 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 artemis keeps my code private?
Agent-S: Cloud APIs (your key) (3/5). artemis: Self-hostable (4/5).
What does each one cost to run?
Agent-S: Your API keys (provider-dependent). artemis: Self-hosted runtime; model usage may incur cloud API costs.
Full profiles: simular-ai/Agent-S and google/artemis. Everything else in Computer use.