Jev in production › Agent tool and action selection

system1-agents

Prebuilt openJiuwen agents in which Jev picks the next browser click, desktop action, game move or support queue from typed options while a chat model plans; installs as a Claude Code or Codex skill and MCP server. Up to 25× cheaper than a chat model (author).

Open on GitHub ↗

25× cheapermeasured against a baseline, as published by the source
Use
Agent tool and action selection
Industry
AI infrastructure
Form
Open-source tool
Stage
In production
Plugs into
Claude Code, Codex
Listed
2026-09-23
Found via
github
Repository
ThinkFlowLab/system1-agents
Stars
132
Forks
22
Last push
2026-10-11
Language
Python
License
Apache-2.0
system1-agents screenshot
docs/assets/stay-tuned.gif in the ThinkFlowLab/system1-agents README, Apache-2.0; shown from GitHub.

The README opens with

[!NOTE] Give your agents a System 1 decision model. Start from a prebuilt agent or build your own. Describe the task. Claude Code or Codex runs a prebuilt agent or builds a new one, on Jev, Laya or Cua-S1 Nano. Browser use, computer use, robotics and games ship ready to run. Up to 6× faster and 25× cheaper than a chat model, at the same score.

scenario Jev chat model speedup Jev cost chat model cost more expensive --------------------- Browser use (Allrecipes)† 35.7 s 138.7 s 3.89× $0.091356 $1.494331 16.4× Custom agent (ticket router, 30 tickets) 12.7 s 65.3 s 5.14× $0.000764 $0.014800 19.4× Computer use (Windows Calculator) 17.2 s 30.1 s 1.75× $0.000447 $0.003002 6.7× Robotics (ALFWorld) 7.4 s 25.7 s 3.47× $0.000221 $0.002800\ 12.7× Games...

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent tool and action selection