- blnk
Content
blnk
A powerful terminal-based chat application for seamless interaction with multiple AI providers.
Features
- Multi-provider support (OpenAI, Anthropic, Google Gemini)
- Rich CLI interface with markdown formatting
- Dynamic model switching and API selection
- MCP integration for advanced reasoning
- Streaming responses with progress indicators
- Command system with help documentation
- YAML configuration with automatic JSON conversion
- Secure API key storage in user's home directory
Installation
Requires Python 3.13 or higher.
- Clone the repository:
git clone https://github.com/frgmt0/blnk.git
cd blnk
- Run the installation script:
./install.sh
This will:
- Create necessary config directories
- Install dependencies
- Set up the default configuration
- Install blnk in development mode
Quick Start
- Run the setup command to configure your API providers:
blnk
/setup
- Follow the prompts to configure your providers and API keys.
Usage
Start blnk:
blnk
Available Commands
/help- Show help message/apis- List available AI providers/use <api>- Switch to specified AI provider/model-list- Show available models for current/all providers/switch-model- Switch to a different model for current provider/tools- List available MCP tools/exit- Exit the application
Examples
/use anthropic # Switch to Anthropic provider
/switch-model claude-3-5-sonnet-20241022 # Switch to Claude 3 model
/tools # Show available tools
Configuration
blnk stores its configuration in ~/.blnk/config/:
config.yaml- Main configuration file (edit this for changes)config.json- Runtime configuration (automatically generated)mcp/*.json- MCP server configurations
MCP Integration
blnk supports integration with MCP (Model Context Protocol) servers. While native MCP-reasoner support is planned for future releases, you can already configure and use MCP servers:
- Create a JSON config file in
~/.blnk/config/mcp/(e.g.,default.json) - Configure the server details:
{
"server": {
"command": "node",
"args": ["path/to/mcp-reasoner/dist/index.js"],
"env": {}
}
}
Multiple MCP servers can be configured by creating additional JSON files in the mcp/ directory.
The configuration includes:
- Default API provider
- Model preferences
- API keys (securely stored)
- Token limits
- MCP settings
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Built with MCP-Reasoner for advanced reasoning capabilities
- Thanks to all contributors
Author
Recommend Clients
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
A Sleek AI Assistant & MCP Client5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .
WindsurfThe new purpose-built IDE to harness magic
HyperChatHyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.
DeepChatYour AI Partner on Desktop
LINKAGOGO-MCP---BOOKMARK-MANAGERManage your LinkaGoGo bookmarks through any AI assistant that supports the Model Context Protocol (MCP). Search, add, organize, tag, move, and export bookmarks conversationally โ 16 tools for full bookmark and folder management. Connect via Claude.ai, Claude Desktop, or any MCP-compatible client.
CursorThe AI Code Editor
LutraLutra is the first MCP compatible client built for everyone
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
y-cli ๐A Tiny Terminal Chat App for AI Models with MCP Client Support
ChatWiseThe second fastest AI chatbotโข
Refact.aiOpen-source AI Agent for VS Code and JetBrains that autonomously solves coding tasks end-to-end.
Roo Code (prev. Roo Cline)Roo Code (prev. Roo Cline) gives you a whole dev team of AI agents in your code editor.
Cline โ #1 on OpenRouterAutonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
ZedCode at the speed of thought โ Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
Cherry Studio๐ Cherry Studio is a desktop client that supports for multiple LLM providers.
MCP ConnectEnables cloud-based AI services to access local Stdio based MCP servers via HTTP requests
chatmcpChatMCP is an AI chat client implementing the Model Context Protocol (MCP).
MCP PlaygroundCall MCP Server Tools Online
Continueโฉ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks