Explore the directory

A pattern language and generation toolkit for building multi-agent systems, installed as a skill for Claude Code, Cursor and similar AI coding agents, which guides the agent through constructing a new system from a catalog of reusable architectural patterns.

• Agent frameworks
• Agent skills

An always-on, voice-controlled desktop agent that manages coding workspaces and background tasks, deciding when a progress update is worth interrupting the user for rather than narrating every step, with support for macOS, Windows and Ubuntu.

• Coding agents
• Speech

A curated list of autonomous AI agents and developer tools built on large language models, organized into categories such as agent platforms, coding assistants, IDEs, LLMOps, prompt tuning and security.

• Curated lists

A cross-platform, terminal-based coding agent CLI for repository-level software development, with persistent sessions, context management, durable project memory and multi-agent collaboration.

• Coding agents

A Python library that stores an AI agent's execution history as Git commits, so every prompt, response and tool call is a version-controlled, inspectable, replayable and forkable event.

• AI evals
• Git

A Claude Code plugin that turns a one-line feature idea into a spec, a dependency-ordered task plan, and reviewed, tested, committed code, running each task in its own git worktree under a five-phase autonomous loop.

• Coding agents
• Agent skills

Six Claude Code skills that encode behavioral discipline for the Opus 4.8 model, covering how it reports progress, when it stops work, what it touches and what it claims, each tested against real Opus 4.8 sessions with the failing transcripts included.

• Agent skills

A self-hosted LLM inference engine written in Rust that runs GGUF models with an OpenAI- and Ollama-compatible API, part of a wider open-source platform for building and distributing EU-based, verticalized language models.

• Inference

An async-first, distributed framework for building multi-agent systems in Python, with an SDK for agent-to-agent communication, example integrations with frameworks such as LangChain, DSPy and LiteLLM, and a demo multi-agent insurance support system.

• Agent frameworks

A configuration-driven fine-tuning framework for Hugging Face Diffusers pipelines, such as Stable Diffusion, where a YAML file describes the whole training pipeline, including which layers to freeze or train, instead of a hand-written training script.

• Models
• Generative media

An unofficial C++ and GGML port of the CosyVoice text-to-speech inference pipeline, focused on CosyVoice3, with zero-shot, instruct and cross-lingual modes and streaming output.

• Speech

A voice-controlled AI agent app for Wear OS smartwatches such as the Galaxy Watch, combining an on-device language model with offline speech recognition and a phone-bridged fallback, so it can answer without a companion phone driving the conversation.

• Agent frameworks
• Mobile

A native macOS chat client for on-device AI, built on Apple Intelligence through the apfel engine, with speech input and output, image analysis through Apple Vision, and local conversation history, requiring no API keys or network access.

• Inference

A research framework, released with its NeurIPS 2026 paper, that pairs a vision-language reasoning model with a JEPA-based world model, so high-level semantic reasoning guides low-level physical prediction for embodied, robotic tasks.

• Models
• Papers

A Python library that compiles neural-network graphs directly into programs for Apple's Neural Engine, bypassing Core ML so that training, not just inference, can run on the chip.

• Inference
• Libraries

A command-line tool from HashiCorp that converts a Terraform provider code specification into Go source for the Terraform Plugin Framework, and scaffolds boilerplate for new data sources and resources from customizable templates.

• CLI tools
• Hosting

A cloud platform and command-line tool for deploying, publishing and monetizing autonomous AI agents as APIs on a shared marketplace, so other developers and businesses can discover and integrate them.

• Agent frameworks
• Hosting

A Go command-line tool that turns an API's OpenAPI, GraphQL or HAR specification into a working, verified toolset for AI agents: a CLI, an MCP server, agent skills, a SQLite cache and hash-verifiable proof artifacts.

• MCP servers
• APIs

A Kubernetes-native checkpoint and restore system for NVIDIA GPU workloads. It saves a fully initialized pod's process and GPU memory, then restores that state on another node so new replicas skip cold start.

• Inference
• Containers

A shape-specialized inference setup that runs the Qwen3.8 Flash Next model across two AMD Radeon AI PRO R9700 GPUs, combining a pinned vLLM fork, GGUF loading and speculative decoding.

• Inference

A minimal keyword-based tool that queries arXiv, OpenAlex and PubMed for new academic papers, deduplicates results across sources, and can translate and summarize them with a language model.

• Papers

A native iOS and iPadOS app that runs GGUF language and vision models fully on-device through llama.cpp, or connects to any OpenAI-compatible cloud API, with keyboard shortcuts for quick replies.

• Inference

A git-native coding agent for Mac that runs entirely locally through Apple's MLX framework, using commits, branches and worktrees as the agent's own state, history and execution model.

• Coding agents

A single web page that runs several AI models entirely inside the browser using hand-written WebGPU kernels, offering chat, image generation, document question-answering and OCR.

• Inference
• Generative media