TaskSync

Tasksync

Reduce premium AI credits cost and manage tasks seamlessly with human-in-the-loop workflows. TaskSync provides three options to integrate feedback loops into your AI-assisted development.

Choose Your Option

Option 1: TaskSync (VS Code Extension) - Recommended

https://github.com/user-attachments/assets/53290a1c-3193-4830-8f13-cb6ae9682a58

A dedicated VS Code sidebar extension with smart prompt queue system. Setup instructions here: tasksync-chat folder.

Features:

• Smart Queue Mode - batch responses for AI agents
• Autopilot - let agents work autonomously with customizable auto-responses
• Agent orchestration toggle - switch between multi-session routing and a single-session lane per workspace
• Remote Access - control from your phone via LAN or Tailscale, with PWA and code review
• Give new tasks/feedback using ask_user tool
• File, folder, tool, and context references with # autocomplete
• Image paste support (copilot will view your image)
• Tool call history with session tracking

Installation: Install from VS Code Marketplace or build from source with npx vsce package.

Option 2: TaskSync Prompt

https://github.com/user-attachments/assets/3d604b0a-a89b-447f-ba87-5539f1f7444d

A terminal-based task agent protocol. Your coding agent actively requests tasks or feedback through terminal commands, executes tasks autonomously, and operates until you stop it.

Features:

• Human-in-the-loop workflow - provide feedback or new tasks
• Terminal-based agent interaction
• Autonomous operation - runs continuously
• Never terminates automatically

Getting Started:

1. Choose your preferred prompt TaskSync Prompt
2. Provide it as context to your AI IDE
3. Send a prompt to the agent
4. Agent executes python -c "import sys; sys.stdin.read()" and waits for input

For spec-driven development, use Specs-Tasksync instead.

Note: Use Ctrl+D (Linux/Mac) or Ctrl+Z + Enter (Windows) to signal end of input.

Option 3: TaskSync MCP Server

This is an MCP server that helps with feedback-oriented development workflows in AI-assisted development by letting users give feedback while the agent is working. It uses the get_feedback tool to collect your input from the feedback.md file in the workspace, which is sent back to the agent when you save. Setup instructions: TaskSync MCP Server

Best Practices (VS Code Copilot)

For GPT models, use TaskSync Extension.

Recommended settings for agent mode:

"chat.agent.maxRequests": 999

Enable "Auto Approve" in settings for uninterrupted agent operation. Sessions beyond 2 hours may produce lower-quality results — TaskSync will warn you when it's time to consider starting a fresh session.

Discussions

The TaskSync community can be found on GitHub Discussions where you can ask questions, voice ideas, and share your prompts with other people. Contributions to TaskSync are welcome and highly appreciated.

Star History

⭐ Drop a star if you find this useful!