GH Repository · simular-ai
Agent-S
Agent S: an open agentic framework that uses computers like a human
- stars
- 12,313
- 30-day movement
- +3311/day
- Related entries
- 60
- Connections
- 1
pythonagent-appPythonagent-computer-interfacecomputer-automationcomputer-useai-agentsgui-agentsplanningmemorycomputer-use-agentmllmretrieval-augmented-generationin-context-reinforcement-learninggroundingcua
Agent S is an open-source agentic framework from Simular AI that operates a computer the way a human would, driving GUI-based computer use. Its topics indicate an agent-computer interface with planning, memory, grounding, retrieval-augmented generation, and in-context reinforcement learning built on multimodal LLMs.
You want an open computer-use agent framework for automating tasks through graphical interfaces rather than APIs.
Use it to
- Automate desktop GUI tasks with an LLM agent
- Build computer-use agents on its agent-computer interface
- Apply planning and memory to multi-step workflows
- Experiment with in-context reinforcement learning
- Use retrieval-augmented grounding for GUI actions
For Developers building computer-use and GUI automation agents
- Role
- agent-app
- Language
- Python
- Licence
- Apache-2.0
- Forks
- 1,446
- Open issues
- 23
- Last push
- 2026-09-05
- Latest release
- v0.1.0 · 2024-11-27
topicscomputer-usegui-agentsplanningmemorygroundingretrieval-augmented-generation