← Discover MCPs and Agents
T
MCPAI & MLGitHub

Terminal-pal

Multi-AI terminal assistant for developers. Supports OpenAI, Claude, Gemini, Groq & Mistral, Ollama with intelligent project analysis, code generation, and elegant blue UI. Features advanced navigation, context-aware responses, auto-save sessions, and professional PDF exports.

Links

README

From the repo.

AI Terminal Pal v2.0 – Supreme Developer Edition

"Your all-in-one terminal-based AI dev sidekick — engineered for speed, clarity, and control."
✨ Powered by: GPT‑4o, Claude 3 Opus, Gemini 1.5 Pro, Groq, Mistral, Ollama and more...
💡 Designed & crafted with precision by Vishnupriyan P R

Built on - Python Maintained - yes Terminal App License-MIT


Overview :

AI Terminal Pal isn't your typical CLI toy... — it's a full-blown developer productivity engine built into your terminal. Whether you're asking quick questions, analyzing codebases, generating boilerplate, or debugging a tangled mess, this tool understands your workflow. With multi-AI provider support, blazing speed, code-aware context building, and beautiful terminal output, it adapts to how you work.


Alt

Features at a Glance

  • 🤖 Multi-AI Support: GPT-4o, Claude 3, Gemini 1.5, Mistral, Groq Llama3, Ollama, and more
  • 🧠 Contextual Intelligence: File-aware responses using @filename.py or auto-scan
  • 🖼️ Themes & UI: Dynamic banner, themed layouts (Professional, Forest, Ocean, Minimal)
  • 📋 Clipboard Smartness: Auto-copy responses; paste into code right away
  • 📦 Project Integration: Code analysis, tree view, metrics, and documentation generation
  • 📊 Live Stats: Track tokens, cost, speed, and query logs
  • 🧪 Built-in Dev Tools: Linting, testing, formatting, and debugging (AI-assisted)
  • 📤 Export Everything: Generate PDFs, logs, reports, or backups from the CLI

Folder Structure

ai-terminal-pal-/📂
├── ai_terminal_pal.py    # Main app
├── .env                    # API keys (optional, or added during /setup)
├── README.md               # You're reading this
├── requirements.txt        # All dependencies

Installation

git clone https://github.com/vishnupriyanpr/Terminal-Pal
cd Terminal-Pal
pip install -r requirements.txt

Set your API keys in .env or input manually via /setup:

OPENAI_API_KEY=sk-...
GEMINI_API_KEY=...
CLAUDE_API_KEY=...

Usage

python ai_terminal_pal.py

Command Examples:

/setup                 # Launch the setup wizard
/ask What is LangChain?   # Ask a quick AI query
/scan                  # Analyze current project
/theme forest          # Apply the 'forest' theme
/attach app.py         # Attach file for AI context

Use /help or /nav to explore all commands.


Supported Providers

This app is multi-AI out of the box. You can pick your preferred model during /setup.

ProviderExample ModelsMax ContextSpeed
OpenAIgpt-4o, gpt-4-turboUp to 128k🔥 Fast
Claudeopus, sonnet, haikuUp to 200k🚀 Blazing
Gemini1.5-pro, flash, proUp to 2M⚡ Snappy
Groqllama3, mixtral, gemma~32k⚡ Ultra-fast
Mistralcodestral, mistral-large~32k💡 Smart
Ollamaany model you initialize~32k +🏠 Local

Theming System

Customize the terminal look with:

  • 💼 Professional
  • 🌊 Ocean
  • 🌿 Forest
  • Minimal

Change themes using:

/theme forest

Sample Session Stats

🧠 Provider: GPT-4o
⏱️ Time Taken: 1.45s
🔢 Tokens Used: 1,152
💰 Estimated Cost: $0.0042
📁 Files Contextualized: utils.py, routes.py

Command Categories

CategoryCommands
Setup/setup, /provider, /theme, /config
AI Interaction/ask, /chat, /generate, /explain, /improve
Project Tools/scan, /tree, /metrics, /analyze, /deps
File Ops/attach, /read, /write, /edit, /backup, /compare
Dev Utilities/lint, /test, /debug, /docs, /format
Export/Logs/pdf, /export, /report, /history, /logs
System/status, /monitor, /clear, /exit, /update

Privacy & Security

  • API keys stored locally in your config directory or .env
  • No telemetry, no tracking — fully offline except for API calls
  • Full transparency in logging and history
  • Optional backup/restore for peace of mind

Sample Interactions

/ask Give me a FastAPI boilerplate
/ask @views.py — optimize this
/ask Explain difference between multiprocessing and multithreading

License

This project is licensed under the Apache 2.0 License.


Credits

Vishnupriyan P R

“Tools should disappear into the background and let you build.”

— Vishnupriyan P R, caffeinated coder ☕

Collected info

  • 21 stars
  • 1 forks
  • Language: Python
  • Source updated: 4/13/2026

Config for your environment

Replace {MCP_ENDPOINT_URL} with this MCP’s endpoint URL (from its repo or docs above). No API key — you connect directly.

Tool

OS

Config file: ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "url": "{MCP_ENDPOINT_URL}"
    }
  }
}

Paste into mcpServers in the config file. Restart Cursor after saving.

If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.