Explore the directory

A framework-agnostic memory runtime that lets an AI agent store and later recall facts, episodes and what worked before, using local embeddings by default or a Postgres backend for production scale.

• Agent memory

A local search engine that indexes images, video and other hard-to-search files using OCR, speech-to-text, image embeddings and automated tagging, letting several models' results sit side by side at search time.

• RAG
• Databases

A maintained JSON database of every known Model Context Protocol client and which protocol features each one supports, so an MCP server can decide how to respond without relying only on the handshake.

• MCP servers

A library that generates short, memorable word-based identifiers for AI agents to pass through prompts and logs, using fewer tokens than a UUID and configurable collision resistance.

• Agent memory
• Libraries

A set of AI coding-assistant skills for Magento 2 development with the Hyva theme, teaching an assistant how to build Hyva child themes, modules and CMS components correctly.

• Agent skills
• Web frameworks

A written set of quality standards and a convergence procedure that any language model can run itself through, so its output is judged against explicit rubric lines and fresh-eyes verification instead of a vague request to make it good.

• Agent skills
• Code quality

A skill that lets an AI agent read, control and take screenshots of a user's own Safari browser on macOS through AppleScript, without a browser extension or a separate automated browser instance.

• Agent skills
• Browser automation

A curated, opinionated set of recommendations for building Model Context Protocol servers and clients, covering tool naming, architecture, testing, deployment, security and performance.

• MCP servers
• Curated lists

A bilingual, continuously updated course covering Claude Code and OpenAI Codex, from first installation through prompt engineering, subagents, MCP servers and full example web projects.

• Tutorials

A local-first workbench for Apple Silicon that brings agent sessions, model comparison, fine-tuning, benchmarking and runtime monitoring for local MLX and remote language models into one interface.

• Models
• Inference

A PDF extraction tool that checks its own output for dropped or scrambled pages and re-extracts them with a stronger backend, and can also audit any other extractor's output for the same silent failures.

• RAG
• Data engineering

A neural-network quantization and inference toolkit that measures how sensitive each part of a model is, assigns it just enough precision to fit a memory budget, then serves the packed result with CUDA and Metal kernels.

• Models
• Inference

An MCP server that answers questions about large CSV, Excel, Parquet and JSONL files by querying an indexed profile of the data instead of pasting the rows into a model's context window.

• MCP servers
• Data engineering

An agent skill that gives an AI assistant deepfake detection and media-forensics abilities, analyzing audio, images, video and text for signs of AI generation through Resemble AI's APIs.

• Agent skills
• Security

A worked example of using AI coding assistants such as Cursor or Claude Code to build NVIDIA DeepStream SDK video analytics applications, using a curated agentic skill and structured prompts.

• Agent skills
• Tutorials

A minimal, OTP-native agent loop for Elixir that sends messages to any language model, executes its tool calls and repeats until done, leaving sessions, memory and scheduling to the application built on top.

• Agent frameworks

An MCP server that searches global patent databases and peer-reviewed scientific literature in natural language from inside Claude, Cursor or another MCP-compatible client, returning results as AI-readable markdown.

• MCP servers
• APIs

A desktop and mobile companion app that lets a user talk to their n8n instance in three modes, from a thin chat client up to a local planning agent that edits files using existing n8n workflows as its tools.

• Workflow automation

Research code implementing least-squares binary quantization of neural networks in PyTorch, with configs and scripts for reproducing the paper's MNIST, CIFAR-100 and ImageNet results.

• Models
• Papers

An MCP server that lets an AI assistant search and manage a Kibana instance's saved objects using natural language, over either a local stdio connection or a remote HTTP endpoint.

• MCP servers
• Monitoring

A code repository accompanying a paid course, covering LLM architecture, ChatGPT API usage, latency and cost comparisons, and hands-on Jupyter notebooks on prompt engineering.

• Tutorials

A cross-platform AI agent orchestrator written in C++ that runs the same engine as a native build on servers, phones and tablets, with a web control panel, scheduler and skills you extend using plain Markdown files.

• Agent frameworks

A Korean-language browser workbench for the Hermes coding agent, adding one-click setup packs, saved artifacts, a personalized start screen built from the agent's own memory, and support for both local and remote models.

• Agent frameworks

A Python framework for building and running AI agents at scale, combining a typed agent core with cost-aware model routing, persistent memory, MCP-native tool calling and durable, resumable workflows.

• Agent frameworks