NanmiCoder/cc-haha
Cc Haha
cc-haha is a cross-platform desktop agent and computer use framework that enables large language models to control local operating systems through screenshots, clicks, and keystrokes. It functions as an AI coding workbench and orchestration platform, allowing for the management of multi-project workflows and the coordination of multiple agents executing complex tasks in parallel.
The system includes a model backend gateway to connect various artificial intelligence providers and local models to autonomous agents. It features a centralized permission gate for authorizing sensitive commands and a side-by-side diff visualization tool for verifying automated code edits.
The platform covers broad capability areas including AI-assisted software development, remote desktop control via token-based sessioning, and the extension of agent skills through a plugin-driven architecture. It also provides tools for scheduling background tasks and monitoring token usage.
Features
- Desktop AI Agents - Acts as a cross-platform desktop agent that enables LLMs to interact with local software and system environments.
- Computer Use - Provides a framework enabling AI models to interact with desktop GUIs and local operating systems.
- Multi-Agent Coordination Systems - Provides a framework for multiple specialized agents to collaborate on complex tasks by sharing state.
- AI Agent Orchestrators - Organizes and coordinates groups of specialized agents using structured workflows for complex projects.
- Multi-Agent Orchestration Platforms - Provides a platform to coordinate and manage teams of specialized AI agents executing complex tasks in parallel.
- Model Provider Integrations - Provides unified interfaces for connecting and configuring multiple third-party and local AI model providers.
- Agent Team Orchestration - Manages the orchestration and coordination of groups of AI agents executing parallel tasks.
- Model Gateways - Provides a centralized gateway service to standardize communication between autonomous agents and various AI model providers.
- AI Coding Assistants - Operates a graphical workbench to oversee multi-project AI-driven coding workflows.
- Coding Workbenches - Ships a graphical workbench for managing multi-project workflows and verifying automated code edits across different operating systems.
- Desktop Application Automation - Automates interactions within desktop applications using screenshots, clicks, and keystrokes.
- AI-Assisted Development - Integrates AI agents into the software development lifecycle via an agentic workbench.
- OS-Level Input Emulators - Implements system-wide hardware event simulation to control the host operating system via AI agents.
- Agent Skill Extensions - Allows the dynamic addition of modular capabilities and custom workflows to autonomous agent systems.
- Agent Capability Extensions - Expands agent functional capabilities through modular plugins and custom tool integrations.
- Remote Control Layers - Implements a management layer to trigger and monitor local agents from remote devices via secure sessioning.
- Model Provider Configurations - Provides interfaces for configuring external AI model providers, credentials, and model selection.
- Model Routing Layers - Includes a middleware layer that abstracts various AI providers to route tasks to specific models.
- Change Review Interfaces - Ships an interactive interface for visualizing diffs and reviewing agent-driven code changes.
- Side-by-Side Diff Viewers - Ships a dual-pane interface for visualizing and verifying automated code modifications.
- Authorization Gates - Provides centralized checkpoints to evaluate and require manual approval for sensitive system commands.
