Explore the directory

A modular collection of tools, function pipelines and filters that extend an Open WebUI instance with research search, image and music generation, and autonomous agent pipelines.

• Agent skills
• Generative media

A command-line tool, also runnable in the browser through WebAssembly, that degrades a PDF to look like a physical scanner output, with adjustable skew, grain, blur, and paper tone.

• CLI tools

A thin MCP server that connects coding agents to a running Next.js dev server, proxying its built-in MCP endpoint for live runtime errors, routes and logs.

• MCP servers
• Debugging

A single-file, pure Java implementation of Llama 3, 3.1 and 3.2 inference, built as a successor to llama2.java and used to test JVM compiler optimizations.

• Inference

A prototype code generator that creates a Go struct from a sample XML document, intended to make reading XML in Go quicker to set up than writing structs by hand.

• CLI tools

A minimalist, terminal-native coding agent written in C, distributed as a single small binary, built for developers who run local models and want to audit exactly what their tools do.

• Coding agents

A web interface for the Pi coding agent that keeps agent sessions running in real workspaces on a user's machine or server, supervised from any browser.

• Coding agents

A Swift package for building tools and applications with large language models and vision-language models using MLX Swift, with LoRA and full fine-tuning support.

• Models
• Libraries

A multi-agent world engine where defined roles, rules and consequences let AI agents interact until useful behavior emerges, usable for research simulations, games and fictional scenarios.

• Agent frameworks

A pure Rust implementation of Mistral's Voxtral Mini 4B speech recognition and text-to-speech models, running natively or in the browser through the Burn machine-learning framework.

• Speech

A terminal-native coding agent, written in Rust, that routes execution, reasoning, context-compaction, self-critique and vision workflows to independently configured models rather than one single model.

• Coding agents

A Go SDK and model server for hardware-accelerated local inference, wrapping llama.cpp, whisper.cpp and stable-diffusion.cpp behind high-level Go APIs and OpenAI- and Anthropic-compatible endpoints.

• Inference

A Chinese-language tutorial site that breaks down the Pi coding agent's source code into core concepts, then walks through building a teaching version of an agent in TypeScript, React and Node.js.

• Tutorials

A security-governance layer for OpenClaw and other agentic AI runtimes that scans capabilities before use, inspects runtime traffic, and exports durable audit evidence.

• AI evals
• Security

A local security-scanning agent for AI-written software that finds issues across code, agent configuration and secrets, then investigates whether each one is real before reporting it as evidence.

• Security

A self-hosted, browser-based AI workspace built on the Pi coding agent, letting a user edit files, run commands and review results in one window, with persistent conversations and scheduled tasks.

• Coding agents

A single native binary that runs the full, unpruned 2.8-trillion-parameter Kimi K3 model on consumer hardware, using small draft models only to speed up generation, never to reduce quality.

• Inference

A terminal application that connects local Ollama models to one or more MCP servers, supporting agent mode, multi-server setups, model switching and human-in-the-loop tool approval.

• MCP servers
• Inference

An MCP server that gives an AI assistant accurate, real-time data on NixOS packages, options, Home Manager, nix-darwin, Nixvim, NVF, FlakeHub and Nix functions.

• MCP servers

An AI-powered code generation agent that runs from the terminal, generating code and explaining its reasoning, with support for running many parallel agent sessions at once.

• Coding agents

A schema-driven framework for defining a web service's API once and generating matching, fully typed server and client code in Go, TypeScript, JavaScript, Kotlin, Dart, Swift, and OpenAPI.

• APIs

An MCP server that lets an IDE run SQL, manage schema migrations and call the Supabase Management and Auth Admin APIs, with built-in safety controls, no longer actively maintained.

• MCP servers
• Databases

A self-healing runtime that wraps an AI agent's function calls, diagnoses failures such as a rejected payment, tries a fix, and remembers the fix so the same error resolves instantly next time.

• Agent frameworks
• Debugging

A Postgres server and extension that automates turning table text into embeddings and provides hooks into popular LLMs, for full-text, semantic and hybrid search.

• RAG
• Databases