Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-09-18 · high
It hands the tab back at a captcha or login and resumes after, and gained 1,319 GitHub stars in one day.
Why now: Tencent cut the bsk CLI's 0.3.0 release on September 17, a day before BrowserSkill's star count passed 4,863 on September 18.
BrowserSkill hands an AI agent a tab from your logged-in Chrome, cookies and session already in place, instead of starting from a blank profile. That means the agent skips logging in itself, and you skip handing over credentials.
When the agent hits a captcha, login prompt, or confirmation dialog, it hands the tab back and resumes once you clear it. Tencent built that handoff into BrowserSkill, an MIT-licensed CLI and Chrome extension. The repo doesn't say how it behaves on sites built to detect and block automation outright.
The agent works in a separate, visible Agent Window. You can watch what it's doing without losing your browsing session. It plugs into Claude Code, Codex, Cursor, OpenClaw, Pi, and anything else that can run shell commands.
The repo, created June 22, gained 1,319 stars in a single day and passed 4,863 total. Tencent cut the bsk CLI's 0.3.0 release the day before.
Each link below shares sources, entities, or timing with this story.
v0.10.0 (~84.8k stars, Apache-2.0) ships no agent of its own and drives whichever CLI you already have, Claude Code, Codex, Cursor, Copilot, OpenClaw, Gemini, Kimi, Qwen, Cline, plus BYOK OpenAI-compatible endpoints, via od mcp install <agent>. It produces single-page HTML pro...
affaan-m/ECC (36.3k forks, MIT) bundles 67 agents, 284 skills, 94 legacy command shims, and "instincts", patterns learned from prior sessions with confidence scores that auto-recall when relevant, plus a .ecc/memory/ markdown vault that's explicitly cross-harness, so context s...
QM went up under MIT license. Created July 29. As of the GitHub API check: 8,420 stars, 887 forks. Five days. YC uses it internally across accounting, legal, events, and engineering, including to build QM itself. Every employee and every Slack room gets its own scoped memory,...
I check Product Hunt maybe once a week and usually regret it. Today's board is worth reading as market structure. The July 30 leaderboard: SKI at 277 upvotes (free voice input for Claude Code and Codex). AI Search Console at 249 (prompt analytics and citation mapping). Memmy A...
+7,546 stars this week for an "Application Development Environment" running each concurrent agent in its own worktree. Works with any terminal CLI agent — Claude Code, Codex, OpenCode, Pi, Cursor, Copilot, Grok, 30+ others — across macOS, Windows, Linux, iOS via App Store/Test...
OpenCLI is at 27,376 stars, installing as the opencli-browser skill in Claude Code, Cursor, and others, driving your already-authenticated Chrome through a Browser Bridge extension over the DevTools Protocol. Credentials never leave the browser and traffic looks like normal us...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.