LLM front ends
Chat, general tasks, and coding agents
- Hermes agent
- Lemonade
- OpenWebUI : User-friendly AI Interface supporting multiple backends.
- oikb : Keep your Open WebUI Knowledge Bases in sync.
- Unsloth desktop
- TinyWebUI
Coding agents
- OpenCode and OpenChamber.
- Minimax code by Minimax.
- Qwen code by Qwen.
- pi coding agent: a minimalist agent. See also oh-my-pi for a preconfigured pi agent.
Deepseek
Deepseek harness
Deepseek harness (DSH) is the official harness for Deepseek and supports other backends.
- dsh-TUI : DSH’s officially top-recommended TUI plugin
- dsh-pet : Desktop companion
- dsh-deep-whale : Whale-chan theme
- dsh-context : context insight and management
MCP servers
The Model Context Protocol (MCP) is an open standard and open-source framework introduced by Anthropic in November 2024 to standardize the way artificial intelligence (AI) systems like large language models (LLMs) integrate and share data with external tools, systems, and data sources.
- Awesome MCP Servers
- DuckDuckGo MCP server
- Julia mcp : MCP server for persistent Julia sessions
- Kaimon.jl : MCP server giving AI agents full access to Julia’s runtime via a live Gate.
- xerj : AI search engine and MCP server for bots and agents.
Skills
Agent skills are a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows.
- figures4papers : Agent skills with Python scripts to make high-quality figures for publications
- obsidian-skills : Agent skills for Obsidian. Teach your agent to use Obsidian CLI.
Julia
Running Julia code in with persistent Julia session(s) (with Revise.jl) to save package loading and JIT compilation time.
- JuliaDaemon.jl: installs a
jldskill for AI agents. - repld : stateful and persistent REPL-like kernel for fast incremental iteration.
Last updated on