CNCF Sandbox Project
Clippy, now with some AI
Run a 1-billion parameter LLM on a $10 board with 256MB RAM
Examples of using E2B
VS Code extension for LLM-assisted code/text completion
Local CLI Copilot, powered by Ollama
Application implementation with business use cases
Demystify RAG by building it from scratch
Run Mixtral-8x7B models in Colab or consumer desktops