#3838th of 48 in Agent frameworks and SDKs
llm
CLI and Python library for prompting local and hosted LLMs, logging to SQLite
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 12.6k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
LLM runs prompts and interactive chats against OpenAI, Anthropic, Gemini and other remote APIs, or local models through plugins such as llm-ollama. It logs prompts and responses to SQLite, and supports attachments, schemas for structured output, tool execution, templates, fragments and embeddings. It installs with pip, Homebrew, pipx or uv.
Who it is for: Developers who want to script LLM prompts from the terminal or Python
Strengths
- Plugin system adds remote providers, local models, tools, fragments and embedding models
- Stores prompts and responses in SQLite for later querying
- Works as both a shell command (pipes, stdin, system prompts) and a Python library
- Schemas extract structured JSON from text and images; embeddings commands included
Weaknesses
- Command-line only; no built-in web UI or user accounts
- Anthropic, Gemini and Ollama access each need a separate plugin install
- Does not run models itself; local inference depends on plugins or external servers
- Tool support is basic compared with dedicated agent frameworks
What it needs
- no GPU
- Needs SQLite, Provider API keys or a local model server (e.g. Ollama, LM Studio) via plugins
- Models: OpenAI, Anthropic Claude (plugin), Google Gemini (plugin), Ollama (plugin), OpenAI-compatible endpoints
Also in Agent frameworks and SDKs
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 93 out of 100 |
| 2 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 88 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 87 out of 100 |