The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
System1 Agents
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
Install
$
npx skills add ThinkFlowLab/system1-agentsClaude Code
claude mcp add system1-agents -- npx skills add ThinkFlowLab/system1-agentsCursor / Claude Desktop (mcp.json)
{
"mcpServers": {
"system1-agents": {
"command": "npx",
"args": [
"skills",
"add",
"ThinkFlowLab/system1-agents"
]
}
}
}Install command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →[!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.
Quickstart · From Claude Code or Codex · Benchmarks · Docs
| 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 (2048, 20 moves) | 27.1 s | 68.5 s | 2.53× | $0.000447 | $0.006139 | 13.7× |
| Games (Millionaire) | 15.3 s | 21.6 s | 1.41× | $0.000168 | $0.000892 | 5.3× |
| Games (Blackjack) | 2.3 s | 14.7 s | 6.39× | $0.000021 | $0.000531 | 25.3× |
† The first Allrecipes task of the WebVoyager task set (He et al., 2024, Apache-2.0, attribution in NOTICE): a vegetarian lasagna with over 100 reviews, 4.5 stars or more, for 6. The chat model of that row is Claude Fable 5.1 through OpenRouter; both models pay it for the typed search text and the answer. * Estimated; the chat-model run recorded no cost. Each replay below is the episode behind its row, Jev on the left and the chat model on the right, both on the wall clock. The other Allrecipes runs, longer games and the Google Flights driver comparison with its rerun of 2026-09-23: docs/benchmarks.md.
OmniJev: a decision model that reads the screen
OmniJev (Apache-2.0, Beijing Zhongguancun Academy, CASIA and Zevo) is a
System 1 decision model on Qwen3.5 vision-language backbones (0.8B, 2B, 4B): it answers the same typed questions as
Jev over a screenshot, a video or a robot camera. --model omnijev puts it in the slot of the browser agents, which
then send it a screenshot of the page at every step (docs/decision-models.md).
The clips below are OmniJev's own v1.1 demos with its 4B model: replays of recorded trajectories with the model's probabilities, not s1a runs and not live control. They are shown from the OmniJev repository and keep their upstream terms.
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.