Explore the directory

A C++ and GGUF reimplementation of the Breeze-TTS-2 bilingual English and Mandarin text-to-speech model, supporting voice design, cloning, direction, and experimental voice conversion with a Vulkan backend.

• Inference
• Speech

A local-first desktop coding agent positioned as an alternative to Cursor, Antigravity, and VS Code coding agents, using bring-your-own-key access to local or cloud language models through MCP.

• Coding agents

A collection of 114 runnable Jupyter notebooks that each teach one prompt engineering technique, from zero-shot prompting through chain-of-thought reasoning, few-shot learning, and output formatting, across several LLM providers.

• Tutorials

A personal knowledge base that stores markdown and YAML sources on disk and answers queries with ranked, cited context blocks, following a documented pattern for grounding AI assistants in a person's own notes.

• Agent memory
• RAG

A minimal, async-first Python framework for building LLM applications with only two hard dependencies, offering unified access to dozens of model providers, vector stores, and agent tools.

• Agent frameworks
• RAG

A local, GPU-accelerated code search toolkit for AI coding agents that combines grep-style, semantic, and graph-based retrieval to cut tool calls and cost compared with plain grep and file reads.

• Agent memory
• RAG

A deployment and configuration guide for running Strix, an autonomous AI penetration-testing agent, on Kali Linux, covering reconnaissance, proof-of-concept generation, and multi-provider LLM setup.

• Security
• Tutorials

An auto-updated repository that tracks every new GitHub repository named 'skills' every fifteen minutes, listing each one's language and description to surface naming and adoption trends in the AI agent skill ecosystem.

• Curated lists

A FastAPI and MCP server that turns the source data of the 2009scape game into a queryable SQLite dataset for a wiki front end or an AI agent.

• MCP servers
• APIs

A dependency-free C11 implementation of Meta's Segment Anything Model 3 for image and video segmentation, with a Metal GPU backend and a multithreaded CPU backend.

• Inference

A technical guide documenting how to run local LLM and image-generation inference on an AMD RX 580 GPU through Vulkan, after AMD dropped ROCm support for that hardware generation.

• Inference
• Tutorials

A terminal-based AI coding assistant written in Python and Textual that runs multiple model providers, enforces permission modes before writing files or executing commands, and adds skills, memory, and team collaboration.

• Coding agents

A plugin for the OpenClaw AI assistant that adds background autonomous thinking, persistent memory, and self-improvement, so the assistant investigates problems and shares findings without being prompted.

• Agent skills
• Agent memory

A local AI load balancer that turns a set of Mac and other devices running Ollama into one cluster, auto-discovering nodes over mDNS and routing language-model, image, speech and embedding requests to the best-fit device.

• Inference
• LLM gateways

A complete neural network framework written in pure C, with no Python or CUDA toolkit dependency, that both runs and trains models, including loading and running GGUF files directly.

• Models
• Inference

A self-hosted platform for MCP Apps and agent automations that turns an installed MCP connector into an interactive sidebar UI with live agent data sync, runnable on demand or on a cron schedule.

• Agent frameworks
• MCP servers

A community study guide for the Model Context Protocol Associate certification from the Linux Foundation's Agentic AI Foundation, covering every exam domain with a weighted study plan and practice questions.

• Tutorials

An unofficial Linux port of MiniMax's AI coding assistant desktop app, packaged as a .deb for Debian-based distributions and a .pkg.tar.zst for Arch-based distributions, since MiniMax does not officially support Linux.

• Coding agents

An always-on, self-hosted local AI assistant and coding-agent runtime written in Go that keeps one durable session across a terminal UI, Telegram and MCP tools, with SQLite memory and human approvals.

• Coding agents

A benchmark suite for local large language models on x86 hardware, measuring time-to-first-token, throughput, total duration and memory use across llama.cpp, LM Studio and Ollama backends.

• Inference
• AI evals

A cognitive memory engine for AI agents, written in pure Go, that extracts memories from conversations, builds a knowledge graph of entities and relationships, and decays or consolidates memories over time.

• Agent memory

A personal AI workspace and runtime that acts as a control plane for agent work: a local gateway for chatting with model providers, running Hecate's own tasks, and supervising external coding-agent sessions with approvals and full tracing.

• Coding agents
• LLM gateways

A config-to-code generator that produces a standalone, framework-free Python agent harness fully owned by the developer, with no dependency on LangChain, LangGraph, ADK or HarnessSmith itself after generation.

• Agent frameworks

A Swift and Metal runtime that runs a 120-billion-parameter mixture-of-experts language model on a 16 GB Apple Silicon Mac by streaming only the experts a token actually needs from disk.

• Inference