CBorg-Powered AI Tools

Use ChatGPT, Gemini, Anthropic, Llama3 and more.

Use CBorg LLMs from your own app or build your own LLM-powered programs.

• API Examples
• API_FAQ
• API Swagger Documentation

Reverse proxy service that streamlines the connection between your local machine and the CBorg API server.

Features:

• Automatic Key Injection: Inject API keys automatically from environment variable - no need to save keys in each application
• Automatic Endpoint Routing on LBL-Net: Detects when client is connected to LBL-net and automatically switch to locally-routed endpoint, reducing latency.
• Usage Monitoring: Periodically checks and reports on current key budget utilization.

Use the popular VS Code Continue Plugin with the CBorg API Server.

Two options:

1. Easy setup: provides chat and editor functions
2. Advanced setup: full functionality with tab-autocompletion and indexing - requires CBorg Client Proxy

Cursor is an AI-powered code editor, based on a fork of VS Code. Cursor requires less setup to configure compared to VS Code + Continue, but is dependent on a Cursor Pro subscription for full functionality including “Composer” and “Fill-in-the middle” code completions.

Cursor can be used with the CBorg API for chat, inline code generation and editing.

Setup Instructions

Go to “Models” in the Cursor Settings:

Step 1: Add CBorg Model Names

1. Disable Default Models: Disable all of the default model names
2. Add CBorg Model Names: Add and enable at least one of the following models:

• lbl/cborg-coder:latest
• openai/chatgpt:latest
• google/gemini:latest
• anthropic/claude:latest

Step 2: Set API Key and Base URL

1. OpenAI API Key: sk-… (paste your CBorg API Key here)
2. Override OpenAI Base URL: https://api.cborg.lbl.gov

If using the CBorg Client, set API Key to “none” and OpenAI Base URL to http://127.0.0.1:8001

Coding assistant capable of editing files in-place using simple commands. Best results with Claude Sonnet, but you can also use the on-prem CBorg Coder model.

To setup, change main.py endpoint and models as follows:

client = OpenAI(
    base_url="https://api.cborg.lbl.gov",
    api_key=os.getenv("CBORG_API_KEY"),
)

DEFAULT_MODEL = "lbl/cborg-coder:latest"
EDITOR_MODEL = "lbl/cborg-coder:latest"