InnerVault

Library

88,213 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.

Results

Looks like a goal we have a starting path for: I want to build an AI agent

  1. agent-skills

    Skills

    Official Agent skills of Oxylabs products

    Stale oxylabs · via GitHub 877 ★MITUpdated 10 days ago

    Source for agent-skills (opens github.com) git clone https://github.com/oxylabs/agent-skills.git
  2. AIPex

    Skills

    AIPex: AI browser automation assistant, no migration and privacy first. Alternative to Manus Browser Operator、 Claude Chrome and Agent Browser

    Stale AIPexStudio · via GitHub 1,268 ★MITUpdated 2 months ago

    Source for AIPex (opens github.com) git clone https://github.com/AIPexStudio/AIPex.git
  3. omowright

    Skills

    Playwright, but built for AI agents: the browser API models already know, token-efficient a11y snapshots, and scroll-driven collection over the network. Zero-port CDP underneath.

    Indexed code-yeongyu · via GitHub 18 ★MITUpdated today

    Source for omowright (opens github.com) git clone https://github.com/code-yeongyu/omowright.git
  4. jev-social

    Skills

    Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence.

    Stale socai-io · via GitHub 205 ★MITUpdated 11 days ago

    Source for jev-social (opens github.com) git clone https://github.com/socai-io/jev-social.git
  5. Open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems.

    Stale feder-cr · via GitHub 32.2k ★MITUpdated 25 days ago

    Source for invisible_dots (opens github.com) git clone https://github.com/feder-cr/invisible_dots.git
  6. A multi-agent AI coding workspace and orchestration environment for Pharo Smalltalk, featuring native and mobile-friendly Web UI

    Indexed mumez · via GitHub 13 ★Updated today

    Source for pharo-agentic-browser (opens github.com) git clone https://github.com/mumez/pharo-agentic-browser.git
  7. agent-skills

    Skills

    A curated collection of reusable agent skills for design, research, browser automation, and developer tooling.

    Indexed archibate · via GitHub 16 ★Custom licence (see repository)Updated 2 days ago

    Source for agent-skills (opens github.com) git clone https://github.com/archibate/agent-skills.git
  8. mearl

    Skills

    A browser work environment for AI agents: automate, debug, and verify in the browser of your choice.

    Indexed mearlhq · via GitHub 10 ★Apache-2.0Updated yesterday

    Source for mearl (opens github.com) git clone https://github.com/mearlhq/mearl.git
  9. vibesurfer

    Skills

    A browser for LLMs, not humans.

    Indexed frane · via GitHub 17 ★Apache-2.0Updated today

    Source for vibesurfer (opens github.com) git clone https://github.com/frane/vibesurfer.git
  10. yeli

    Skills

    A browser-based Markdown editor for people and AI agents. Portable HTML documents with offline editing. Online editor in development. | 页里:人和 AI 都好用的 Markdown 编辑器。离线单文件,在线编辑器开发中。

    Stale whitesmell · via GitHub 5 ★MITUpdated 22 days ago

    Source for yeli (opens github.com) git clone https://github.com/whitesmell/yeli.git
  11. e2e-skills

    Skills

    Playwright and Cypress E2E testing skills for AI agents. Generate Playwright tests, review test quality, and debug failures in Claude Code and Codex.

    Stale voidmatcha · via GitHub 26 ★Apache-2.0Updated 11 days ago

    Source for e2e-skills (opens github.com) git clone https://github.com/voidmatcha/e2e-skills.git
  12. firefox-cli

    Skills

    Let AI Agents control your real firefox browser: fill forms, authenticate, automate actions, web development; all via token-efficient, easy to use CLI. Claude plugin / Codex skill included. agent-browser, but for Firefox chads.

    Stale respawn-llc · via GitHub 24 ★AGPL-3.0Updated 33 days ago

    Source for firefox-cli (opens github.com) git clone https://github.com/respawn-llc/firefox-cli.git
  13. Browser automation with evidence. An Agent Skill that lets an AI agent drive a real browser while every action passes a policy gate, every run leaves an auditable artifact, and the run compiles into a plain Playwright script that replays for free.

    Stale OMD-123 · via GitHub 13 ★MITUpdated 5 days ago

    Source for browser-verified-skill (opens github.com) git clone https://github.com/OMD-123/browser-verified-skill.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.