Auto-generated — not yet edited · only the numbers are verified
- TESIGN / RADAR
- REPOSITORY CARD
- agentrhq/webcmd
agentrhq/webcmd
Self-learning agent browser
RANKS Rising 7d #52 · Rising 30d #96
AT A GLANCE
- LANGUAGE
- TypeScript
- LICENSE
- Apache-2.0
- USAGE
- Commercial use, redistribution OK. Keep notices; mark changes.
- ACTIVITY
- last commit 5 days ago ()
- TOPICS
- ai-agents
- browser-automation
- browser-use
- cli
- developer-tools
- playwright
- self-learning-ai
- HOMEPAGE
- https://webcmd.dev
- REPOSITORY
- GitHub ↗
- CATEGORY
- AI
A summary, not legal advice.
README EXCERPT
Webcmd Self-learning browser infra for AI agents. Webcmd learns the navigational context of websites as agents use them, then turns that knowledge into local memory for faster, cheaper, more reliable browser automation. The goal is simple: stop making agents rediscover the same sites on every run and cut browser-agent token spend by up to 90%. Webcmd pairs live browser control with a self-learning memory layer: Layer Scenario What Webcmd Helps With --- --- --- 0. Live browser control The site is unfamiliar. Use webcmd browser to inspect, click, type, extract, capture network calls, and complete the task in a real browser. 1. Sitemap memory The site is familiar, but the action space is not fully known. Capture an agent-facing sitemap of observed pages, states, actions, workflows, APIs, pitfalls, and fallback paths. Demo https://github.com/user-attachments/assets/bdb65307-9e2a-4d58-9175-45d59528ae37 Quick Start Agent prompt Manual Webcmd requires Node.js 20.6+. When prompted, choose Claude, Codex, another supported harness, or a custom skills path. That installs exactly one skill, webcmd-browser . Load or tag webcmd-browser only for live browser work, then describe the outcome you wa…
The opening of the GitHub README as stored, at most 1,200 characters. Markdown is not rendered.
TIMELINE
- Repository created
- Last push
- FIRST SEEN BY TESIGN ◌ BACK CATALOG
AI chooses the lists under the owner’s delegation. No human review is running in September 2026. Total stars, increases, cross-source signals, last updates and licences are shown as evidence. How ranks work →
If this repository gets editorial text (why, build, who, start, caveat) it becomes an edited entry. Until then the page shows only stored GitHub metadata and numbers.