Explore the directory

A real-time monitoring dashboard and auto-generated wiki for the Hermes AI agent, showing live sessions, tool calls and activity while also documenting the agent's installed skills, plugins, tools and configuration.

• Monitoring
• Documentation tools

A reproduction kit for serving GLM-5.3-Flash, a 320-billion-parameter mixture-of-experts model, in production across two NVIDIA DGX Spark machines with a 1,000,000-token context window and documented fixes for prefix-cache misses.

• Inference

A continuously refreshed, publicly aggregated list of free HTTP, HTTPS, SOCKS4 and SOCKS5 proxies, each tested and labeled with country, anonymity grade, latency and uptime.

• Networking

A collection of command-line tool skills for AI coding assistants such as Claude Code, Codex and Antigravity CLI, covering web search, semantic code search, delegating tasks between agents, literature search and other developer utilities.

• Agent skills

A single C++ binary, built on ggml, for text and document understanding: embeddings, sparse and multi-vector retrieval, reranking, optical character recognition, layout analysis, and named-entity extraction, with no Python or ONNX runtime required.

• RAG

A drop-in, Playwright-compatible Model Context Protocol browser-automation server that runs the unchanged upstream Playwright MCP tool surface against CloakBrowser's Chromium build, packaged for npm, Docker and Streamable HTTP.

• MCP servers
• Browser automation

A reference collection of the Claude Fable 5 system prompt, together with vendor-neutral English and Chinese rewrites that strip out product-specific details for reuse as a system prompt in other assistants.

• Agent skills

A local, deterministic tool that assembles a ranked, token-budgeted bundle of code context for AI coding agents up front, along with a receipt recording what was included, what was skipped, and whether the bundle is complete enough to act on.

• Agent memory

An agent-driven framework that automates GPU kernel optimization by pointing a coding agent, currently Claude Code, at a kernel operator and letting it iterate inside an isolated workspace using profilers and per-language knowledge the framework provides.

• Coding agents
• Agent frameworks

A local AI companion for Windows, macOS and Linux with persistent per-project memory, an integrated code editor, and 30 or more built-in tools, positioned as a personal alternative to general-purpose agent frameworks.

• Coding agents

A ComfyUI extension that quantizes diffusion models to low-bit formats such as W4A4, W4A8 and W8A8, loads pre-quantized checkpoints and quantization-aware LoRAs, and tunes inference for low-VRAM GPUs.

• Inference
• Generative media

A command-line tool, modeled on the Unix du command, that reports how many language-model tokens each file and directory in a project consumes, to help budget context before feeding a folder to an LLM or coding agent.

• CLI tools

An autonomous AI command center for penetration testing and security research that runs recursive tool-calling loops against a target with real-time streaming output, a local memory store and a choice of LLM backends.

• Security

A collection of runnable quickstarts and feature demos for the CrewAI multi-agent framework, each a self-contained Jupyter notebook or Python example meant to be extended for a developer's own project.

• Agent frameworks
• Tutorials

A layer-streaming inference tool that runs large diffusion image, image-editing and video-generation models on GPUs with as little as 4 GB of VRAM, without quantizing the model weights.

• Inference
• Generative media

A local, privacy-first inference server that separates fact storage from language composition, retrieving facts from plain markdown files with a small keyword index instead of relying on a large model's memorized weights.

• RAG
• Inference

A local-first fleet manager for command-line coding agents that runs Claude Code, Codex, Cursor, OpenCode and Pi unattended in pseudo-terminals, with one dashboard to watch, message and automate the whole fleet.

• Coding agents

An extension for the Pi coding agent that adds a faster response mode, OpenAI subscription usage visibility, image generation and animated footer pets for OpenAI-based workflows.

• Coding agents

A reverse proxy for LLM APIs that detects personal data in outgoing requests, replaces it with deterministic tokens before it reaches the model provider, and restores the original values in the response.

• LLM gateways
• Security

A lightweight Android library for running language, vision, speech and image-generation models entirely on-device, built on llama.cpp and related C++ inference engines.

• Inference
• Mobile

A cross-platform man-in-the-middle proxy that intercepts, logs and analyzes the traffic between AI coding tools such as Claude Code, Cursor, Codex or OpenCode and their backend language-model APIs.

• Debugging

An early-preview, local-first personal AI agent that runs tasks on a computer through explicit subsystem contracts for model providers, messaging channels, tools, memory and device peripherals.

• Agent frameworks

An AI agent framework, built on LangChain and LangGraph with a fully asynchronous architecture, that lets an agent configure new Model Context Protocol tools, schedule its own background tasks, and manage its own long-term memory.

• Agent frameworks

A management console plugin for DeepSeek Harness's official Model Context Protocol client, adding a settings page to add, edit, remove and test-call MCP servers, plus health diagnostics and status reporting.

• Coding agents
• MCP servers