Show HN: Running LLMs in one line of Python without Docker (lepton.ai) | HN Screenshots

YHacker Newsscreenshots

Screenshot of lepton.ai: Show HN: Running LLMs in one line of Python without Docker

First screen, captured 3 years ago.

Looks similar

Screenshot of github.com: Show HN: I open-sourced my AI toy company that runs on ESP32 and OpenAI realtime

Show HN: I open-sourced my AI toy company that runs on ESP32 and OpenAI realtime (github.com)

109 points by akadeb 1 year ago | 55 comments

Screenshot of github.com: LSP-AI: open-source language server serving as back end for AI code assistance

LSP-AI: open-source language server serving as back end for AI code assistance (github.com)

233 points by homarp 2 years ago | 50 comments

Screenshot of github.com: LangManus: An Open-Source Manus Agent with LangChain + LangGraph

LangManus: An Open-Source Manus Agent with LangChain + LangGraph (github.com)

105 points by gfortaine 1 year ago | 11 comments

Screenshot of github.com: xLSTM code release by NX-AI

xLSTM code release by NX-AI (github.com)

119 points by badlogic 2 years ago | 28 comments

Screenshot of github.com: Show HN: We made our own inference engine for Apple Silicon

Show HN: We made our own inference engine for Apple Silicon (github.com)

145 points by darkolorin 1 year ago | 42 comments

Screenshot of github.com: Show HN: Linggen – A local-first memory layer for your AI (Cursor, Zed, Claude)

Show HN: Linggen – A local-first memory layer for your AI (Cursor, Zed, Claude)(github.com)

12 points by linggen 10 months ago | 5 comments