Skip to content

Commit 3eb8f20

Browse files
committed
docs: restructure AI agents table for better clarity
Split the "AI Agents (Computer Use)" section into "Local Computer Use Agents" and "Cloud / API Computer Use Agents". Add platform-specific columns (Windows, macOS, Linux) to the local agents table to clearly show compatibility. This improves readability and helps users quickly identify agents suitable for their operating system and deployment preference.
1 parent fce4e7f commit 3eb8f20

1 file changed

Lines changed: 24 additions & 13 deletions

File tree

docs/readme.md

Lines changed: 24 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -600,19 +600,30 @@ AI agents and tools for automating desktop tasks and OS-level interactions.
600600

601601
#### AI Agents (Computer Use)
602602

603-
| Agent | Platform | Vision-Based | Cross-Platform | Best For | GitHub |
604-
|-------|----------|--------------|----------------|----------|--------|
605-
| **Agent S** | Cross-platform ||| Research/SOTA | [🔗](https://github.com/simular-ai/Agent-S) |
606-
| **Simular Agent S2** | Cross-platform ||| Latest SOTA, improved grounding | [🔗](https://github.com/simular-ai/Agent-S) |
607-
| **Open Interpreter** | Cross-platform | ⚠️ || Natural language computer control, 63K+ stars | [🔗](https://github.com/OpenInterpreter/open-interpreter) |
608-
| **Bytebot** | Linux (Docker) ||| Self-hosted ||
609-
| **UFO** | Windows ||| Windows automation | [🔗](https://github.com/microsoft/UFO) |
610-
| **Open-Interface** | Cross-platform ||| General use | [🔗](https://github.com/AmberSahdev/Open-Interface) |
611-
| **Anthropic Computer Use** | API ||| Beta capability ||
612-
| **OpenAI Operator** | API ||| Guided browser computer use ||
613-
| **Microsoft Fara-7B** | Cross-platform ||| Open-weight vision grounding model | [🔗](https://github.com/microsoft/Fara) |
614-
| **Amazon Nova Act** | API ||| AWS browser automation SDK ||
615-
| **Manus AI** | Cloud ||| General-purpose cloud agent ||
603+
##### Local Computer Use Agents
604+
605+
Agents that run directly on your machine and interact with the OS, screen, keyboard, and mouse.
606+
607+
| Agent | Windows | macOS | Linux | Vision | Best For | GitHub |
608+
|-------|:-------:|:-----:|:-----:|:------:|----------|--------|
609+
| **Agent S** ||||| Research/SOTA, GUI grounding | [🔗](https://github.com/simular-ai/Agent-S) |
610+
| **Simular Agent S2** ||||| Latest SOTA, improved grounding | [🔗](https://github.com/simular-ai/Agent-S) |
611+
| **Open Interpreter** |||| ⚠️ | Natural language computer control, 63K+ stars | [🔗](https://github.com/OpenInterpreter/open-interpreter) |
612+
| **Open-Interface** ||||| General-purpose desktop automation | [🔗](https://github.com/AmberSahdev/Open-Interface) |
613+
| **UFO** ||||| Windows-specific app automation | [🔗](https://github.com/microsoft/UFO) |
614+
| **Bytebot** ||||| Self-hosted (Docker), headless ||
615+
| **Microsoft Fara-7B** ||||| Open-weight vision grounding model | [🔗](https://github.com/microsoft/Fara) |
616+
617+
##### Cloud / API Computer Use Agents
618+
619+
Agents accessed via API or cloud service — OS-independent, but require internet connectivity.
620+
621+
| Agent | Interface | Vision | Best For | GitHub |
622+
|-------|-----------|--------|----------|--------|
623+
| **Anthropic Computer Use** | API || Beta capability, Claude-powered desktop control ||
624+
| **OpenAI Operator** | API || Guided browser and desktop computer use ||
625+
| **Amazon Nova Act** | API || AWS browser automation SDK ||
626+
| **Manus AI** | Cloud || General-purpose cloud agent ||
616627

617628
#### RPA & Visual Frameworks
618629

0 commit comments

Comments
 (0)