LLMs

Large language models (LLMs), APIs, agents, and harnesses.

• llmspeed : Feel how fast a local LLM runs before you buy the hardware

Models and recipes

See models

Front ends

Chat, general tasks, and coding agents

• Hermes agent
• Lemonade
• Lucebox
• open-webui : User-friendly AI Interface supporting multiple backends.
• Unsloth desktop

Coding agents

• OpenCode and OpenChamber
• Minimax code by Minimax
• Qoder by Qwen
• pi coding agent: a minimalist agent. See also oh-my-pi for a preconfigured pi agent.

Deepseek

• Codewhale: previously called `deepseek-tui
• Deepseek harness (DSH)
  • Deepseek plugins
• Deepseek reasonix : cache-friendly harness for DeepSeek.

MCP servers

Model Context Protocol (MCP)

• DuckDuckGo
• Julia : MCP server for persistent Julia sessions
• Kaimon.jl : MCP server giving AI agents full access to Julia’s runtime via a live Gate.

Skills

• JuliaDaemon.jl: installs a jld skill for AI agents to run Julia code with a persistent Julia session (with Revise).