DSH（DeepSeek Harness）插件：把 ego-lite 浏览器（给 AI Agent 用的 Chromium）接入 HARNESS——13 个结构化 ego_* 工具（文本语义快照、语义定位点击、表单填充、截图、CDP 控制、任务空间隔离），内置 ego 运行时，Linux + Chrome 开箱即用，无需克隆官方仓库或手动构建。
Fast browser agent for ego lite. One TypeSafe request per step; an agent or Jev picks the move.
ego lite skill — each DOM step decided in ~0.4s, no LLM turn
Pluggable decision layer for the ego lite browser: one System One (Jev) call per step replaces the per-step LLM turn, and the backend can be swapped for a local OpenAI-compatible model. Fail-closed execution guards. The measured one — raw bench data, 16 suites, changelog with corrections.
Jev drives your Ego Lite browser: one typed-choice request per step. Single-file, zero-dependency port of browser-use/jev-ultrafast with multi-model benchmarks and extra guardrails. Unofficial.
Ego Lite Browser: New free AI browser runs locally (Playwright alternative) - Rate-limit resilient web trend intelligence collector and breaking AI tools summarizer powered by Citrolabs Ego Lite and Ollama.
Browser use & computer use for coding agents, powered by TypeSafe Jev: calibrated judgments from a System One model, control loop in code. ego lite / Chrome / Safari · CLI + MCP
Hands-on, reproducible benchmarks of AI agent tooling — same machine, same tasks, full scripts
ego lite browser automation for dsh that remembers — recall a site's learned tools, promote a working script into a new one, hand the user the keyboard for real. 7 tools, host-only, MIT.
Automate web tasks with a lightweight, high-performance browser built for AI agents.
Functional Hermes MCP preview for the ego-lite agent browser
Source-blind simulated-user testing skill for Ego Lite on macOS
A powerful meta-skill for AI Agents that records user interactions in ego-browser and automatically converts them into standalone, reusable automation skills.
Claude Code / AI-agent skill: ask OpenEvidence via ego-lite, capture the thread, and mint a shareable HTML + Crossref-verified BibTeX / CSL-JSON / AMA bibliography. Evidence-based-medicine citation export. Install: npx skills add htlin222/ask-oe-with-ego-skill
Build a 0.6B parallel decision model that turns states into probability distributions—no output-token decoding needed.
To associate your repository with the ego-lite topic, visit your repo's landing page and select "manage topics."