LLM is a CLI and Python library for accessing 100+ LLMs via APIs or locally. 11.5K+ stars. SQLite logging, embeddings, structured data. Apache 2.0.
这里应该同时让用户和 Agent 知道第一步该复制什么、安装什么、落到哪里。
# Install
pip install llm
# Or: brew install llm
# Set API key
llm keys set openai
# Run a prompt
llm "Explain quantum computing in one sentence"
# Chat mode
llm chat -m claude-4-sonnet
# Extract structured data
llm "List 3 fruits" --schema name:str,color:str
# All prompts logged to SQLite
llm logsLLM is a command-line tool and Python library for accessing OpenAI, Claude, Gemini, Llama, and dozens of other LLMs through APIs or locally-installed models. With 11,500+ GitHub stars and Apache 2.0 license, it stores all prompts and responses in SQLite for logging and analysis, generates embeddings, extracts structured data using schemas, supports tool execution, interactive chat mode, and multi-modal inputs (images, audio, video) via plugins.
Best for: Developers who want quick LLM access from the terminal with full logging Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf
Q: What is LLM? A: CLI tool with 11.5K+ stars for 100+ language models. SQLite logging, embeddings, structured data, chat mode. Apache 2.0.
Q: How do I install LLM? A: pip install llm or brew install llm. Then llm "your prompt".
Created by Simon Willison. Apache 2.0. simonw/llm — 11,500+ GitHub stars
TaskWeaver is a Microsoft code-first agent framework for data analytics tasks. 6.1K+ stars. Planning, stateful execution, DataFrames, plugins. MIT.
AIChat is a CLI for 20+ LLM providers with shell assistant, RAG, agents, and function calling. 9.7K+ stars. MIT/Apache 2.0.
Khoj is a personal AI app for chat, search, and knowledge management. 33.8K+ stars. Multi-LLM, docs, Obsidian, WhatsApp, custom agents. AGPL-3.0.