AI & Agent Utilities
11The layer specific to running LLMs and agents: model CLIs, context builders, token accounting, sandboxes, and notifications. Tools an agent uses to call other models or prepare its own inputs.
LLM CLIs
- llmSimon Willison's CLI for talking to LLMs (local and hosted); pipe text in, get completions out, with a plugin ecosystem. The default for scripting model calls in a shell.
- AIChatall-in-one LLM CLI (chat, shell assistant, RAG) usable non-interactively; delegate sub-prompts to models.
- Ollamarun open LLMs locally with a simple CLI/API; offline inference for agent subtasks.