Skip to main content
tactus - AI Agents | SkillsLLM
Home AI Agents tactus The first browser AI Agent extension to support Agent Skills, enabling AI to perform complex tasks through an expandable skill system. ๐ Star if you like it! | ้ฆไธชๆฏๆ Agent Skills ็ๆต่งๅจ AI Agent ๆฉๅฑ๏ผ่ฎฉ AI ้่ฟๅฏๆฉๅฑๆ่ฝ็ณป็ปๆง่กๅคๆไปปๅก ๐ ๅฆๆๅๆฌข่ฏท็นไธช Star๏ผ
AI Agentsai ai-agent browser-extension chat chatbot
# Add to your Claude Code skills
git clone https://github.com/Castor6/tactusGuides for using ai agents skills like tactus.
English | ็ฎไฝไธญๆ
Tactus
The First Browser AI Agent Extension with Agent Skills Support
[![Chrome Version][chrome-version-shield]][chrome-store-link]
[![Chrome Users][chrome-users-shield]][chrome-store-link]
[![Firefox Version][firefox-version-shield]][firefox-store-link]
[![Firefox Users][firefox-users-shield]][firefox-store-link]
Tactus is an innovative browser extension that brings the Agent Skills specification to the browser environment, enabling AI Agent to perform complex tasks through an extensible skill system.
Triggering skills can achieve prompt injection for specific scenarios, and common workflows can be encapsulated in scripts for execution, replacing repetitive automated operations of AI Agents. This approach is both fast and token-efficient.
โจ Core Features
๐งฉ Agent Skills System
Tactus is the first product to implement the Agent Skills specification in a browser extension:
Skill Import - Import spec-compliant Skill folders containing instructions, scripts, and resource files
Script Execution - Safely execute JavaScript scripts within pages
Trust Mechanism - First-time script execution requires user confirmation, with option to permanently trust
๐ค Intelligent Conversation
Multi-Provider Support - Native support for Anthropic (Claude), Gemini (Google), and any OpenAI-compatible API provider
- Configure multiple providers and switch models anytime
Sign in with GitHub to leave a comment.
No comments yet. Be the first to share your thoughts!
Related Skills Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
llm
skills
First-time install walkthrough for Claude Code, Codex CLI, and ChatGPT.
Multi-Model Switching
Streaming Response - Real-time AI replies with chain-of-thought display
ReAct Paradigm - Built-in complete tool calling loop, AI autonomously decides when to use tools
Stop Generation - Interrupt ongoing AI generation or tool calls at any time
Tab Lock - Automatically locks the tab during AI responses with a glowing animation to prevent accidental navigation
Preset Quick Actions - Quick action buttons for common prompts in the chat panel
๐ผ๏ธ Image Vision Support
Vision Model Config - Configure vision capability independently per model
Paste Images - Paste images directly in the chat input to send to AI
Multimodal Chat - Support image-text mixed queries, letting AI understand screenshots, charts, and other visual content
๐ Page Understanding
Smart Extraction - Uses Readability + Turndown to extract core page content and convert to Markdown
Selection Quote - Select text on page or in sidebar and quote it with one click
Context Awareness - AI determines whether to call page extraction tool; skips if skill script provides content
Raw Extraction Mode - Configure specific websites to skip Readability algorithm and extract raw page content directly
๐ HTTP MCP Support
MCP Server Connection - Add and manage multiple HTTP MCP Servers
Dynamic Tool Discovery - Automatically fetch available tools from MCP Server and integrate into conversations
Multiple Auth Methods :
No authentication (public services)
Bearer Token authentication
OAuth 2.1 authentication (with auto-refresh)
https://github.com/user-attachments/assets/c7737e7e-dd2e-4888-a030-db40b9731f1d
๐จ Themes & Personalization
Theme Switching - Support light, dark, and system-follow theme modes
Floating Ball Toggle - Freely enable/disable the floating ball on the right side of the page
Selection Quote Toggle - Freely enable/disable the selection quote feature
Internationalization - Support Chinese/English interface switching
๐พ Local Storage
Session Management - Conversation history stored locally with pagination support
Message Editing - Edit sent user messages and regenerate replies
Message Copy - One-click copy for AI replies
IndexedDB - Skills and files stored in local database
Privacy First - All data saved locally, nothing uploaded to any server
โ๏ธ Advanced Configuration
Web Content Char Limit - Configure maximum characters for extracted page content to control token usage
Tool Call Limit - Configure maximum tool calls per conversation to prevent infinite loops
Smart Base URL Handling - Auto-complete /v1/chat/completions path to simplify API configuration
API Endpoint Preview - Preview the full API endpoint URL below the Base URL input
Auto-Save Config - Model provider and MCP server configurations are automatically saved with debounce
Open Links in New Tabs - Links in AI responses open in new tabs to preserve your conversation
๐ Quick Start
Download | Browser | Download |
| ------- | -------- |
| Chrome | [Chrome Web Store][chrome-store-link] |
| Firefox | [Firefox Add-ons][firefox-store-link] |
Install
Chrome / Edge (recommended)
Extract tactus.zip to a permanent directory
Open chrome://extensions/ in Chrome
Enable Developer mode (top right)
Click Load unpacked (top left)
Select the extracted tactus folder
Firefox (temporary debug install)
Run npm run build:firefox
Open about:debugging#/runtime/this-firefox
Click Load Temporary Add-on
Select .output/firefox-mv2/manifest.json
๐ ๏ธ Build from Source git clone https://github.com/Castor6/tactus.git
cd tactus
npm run dev
npm run dev:firefox
npm run build
npm run build:firefox
Please use the Professional style within the .claude\skills\design-style skills to design with a unified extended UI style.
๐ User Guide
Configure AI Provider
Click the extension icon to open the sidebar
Click the settings button to enter configuration page
Add API provider (fill in name, API URL, key)
Fetch model list and select a model
Enable vision config in model settings if vision capability is needed
Import Skill
Find the Skills management area in settings page
Click "Import Skill" button
Select a folder containing SKILL.md
Confirm import and use it in conversations
Configure MCP Server
Find the MCP management area in settings page
Click to add an MCP Server
Fill in Server URL and select authentication method
Once connected, tools provided by MCP will be automatically integrated into conversations
Skill Folder Structure my-skill/
โโโ SKILL.md # Required: Skill definition and instructions
โโโ scripts/ # Optional: Executable scripts
โ โโโ fetch-data.js
โโโ references/ # Optional: Reference documents
โ โโโ api-docs.md
โโโ assets/ # Optional: Resource files
โโโ template.json
SKILL.md Format ---
name: my-skill
description: This is an example skill
---
# Skill Instructions
When user needs to perform a task, follow these steps:
1. First analyze user requirements
2. Call scripts/fetch-data.js to fetch data
3. Organize and return results
๐ ๏ธ Tech Stack
Framework : WXT - Modern browser extension development framework
Frontend : Vue 3 + TypeScript
AI Integration : Native Anthropic (Claude) API, Native Gemini (Google) API, OpenAI SDK (compatible with any OpenAI API)
MCP Support : @modelcontextprotocol/sdk - Model Context Protocol client
Content Extraction : @mozilla/readability + turndown
Storage : IndexedDB (idb) + WXT Storage
Authentication : OAuth 2.1 support (for MCP Server auth)
๐ง Built-in Tools Tactus provides the following built-in tools for AI:
| Tool | Description |
|------|-------------|
| extract_page_content | Extract main content from current page |
| activate_skill | Activate a specified Skill |
| execute_skill_script | Execute script within a Skill |
| read_skill_file | Read file content from a Skill |
| MCP Tools | Dynamically fetched tools from connected MCP Servers |
๐ Development
Project Structure tactus/
โโโ entrypoints/
โ โโโ background.ts # Background script
โ โโโ content.ts # Content script
โ โโโ sidepanel/ # Sidebar UI
โ โโโ options/ # Settings page
โโโ components/ # Vue components
โโโ utils/
โ โโโ anthropic.ts # Anthropic (Claude) API integration
โ โโโ api.ts # API calls & tool execution
โ โโโ db.ts # IndexedDB operations
โ โโโ gemini.ts # Gemini (Google) API integration
โ โโโ storage.ts # Settings & storage management
โ โโโ i18n.ts # Internationalization
โ โโโ mcp.ts # MCP Client management
โ โโโ mcpOAuth.ts # MCP OAuth 2.1 auth
โ โโโ mcpStorage.ts # MCP config storage
โ โโโ skills.ts # Skills core logic
โ โโโ skillsExecutor.ts # Script executor
โ โโโ skillsImporter.ts # Skills import
โ โโโ tools.ts # Tool definitions
โ โโโ pageExtractor.ts # Page content extraction
โโโ public/ # Static assets
57,557
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
AI Agents ai-agents anthropic
CompareThe agent that grows with you
AI Agents ai ai-agent
CompareClaude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
AI Agents
CompareLLM inference in C/C++
AI Agents ggml
CompareAn open-source AI agent that brings the power of Gemini directly into your terminal.
AI Agents ai ai-agents
Compare