Self-Learning Browser WebCMD Goes Open Source with 2.3k Stars, Works with Claude Code
PrajwalTomar_ · x · 2026-09-23
WebCMD (agentrhq/webcmd) is now on GitHub: self-learning browser infrastructure for AI agents, with 2.3k stars and 1.5k forks. It learns websites' navigational context as agents use them and turns that into local memory, making browser automation faster, cheaper, and more reliable.
- Works with Claude Code, Codex, Hermes, OpenCode, or any agent that can run a skill
- Repo includes Claude/Codex plugin directories, MCP skills, and benchmarks
- TypeScript codebase; stated goal is to stop agents from rediscovering the same sites
Related event: WebCMD: Open-Source Self-Learning Browser Infrastructure for AI Agents(2 posts)→
More from coding & agent
- Dev runs 32 coding agents burning 5-10B tokens a day in Zed — generativist · 2026-09-23
- Stanford paper: self-organizing agent team hits 66.7%, beats best single model's 48.8% — dair_ai · 2026-09-23
- Google's ToolGrad reverses tool-use data generation, hits 83.1 BFCL with 12B Gemma-3 — dl_weekly · 2026-09-23
- Using AI agents to book things still costs as much mental effort as doing it yourself — nabeelqu · 2026-09-23
- LangChain to unveil new products Thursday, previewed live at Interrupt keynote — LangChain · 2026-09-23
- axure-mcp-server extracts and OCRs Axure prototypes for LLM analysis — modelcontextprotocol · 2026-09-23