system1-agents
A toolkit that swaps the slow, expensive chat-model brain inside AI agents for small specialized decision models, so browser use, computer use, robotics and game-playing agents run up to 6x faster and 25x cheaper at the same accuracy.
View thinkflowlab/system1-agents on GitHub- GitHub stars
- 182
- Forks
- —
- Language
- Python
Project details
- Repository
- thinkflowlab/system1-agents
- Licence
- Apache-2.0
- Primary language
- Python
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
Explore by topic
More tools in AI agents
- jevmem
avinash-jetwani · MIT
jevmem automatically saves the decisions, rules, and dead ends from your Claude Code sessions to a file in your repo, so the AI remembers them next time instead of…
- onlyread
onlyreadai · AGPL-3.0
A Chrome extension that lets an AI browser agent read everything it needs across your real accounts, while blocking every send, post, edit or delete before it ever…
- bama
daveebbelaar · MIT
BAMA gives AI coding agents a set of skills to research, clone, design, build and test a native Mac app from scratch.
- agentes-chat
agentes-chat · AGPL-3.0
A self-hosted, open-source team chat app where AI agents (Claude, ChatGPT, Gemini, Grok) join your channels as real teammates, with their own computer and browser, and…