Explore the directory

An open, MIT-licensed database of confirmed-malicious IP addresses and disposable email domains, rebuilt every 30 minutes from honeypot sensors and community reports, for use in firewalls, WAFs and signup checks.

• Security
• Databases

A curated list of vector database engines, managed and serverless offerings, SDKs, benchmarking and evaluation tools, and research papers for building AI applications.

• Databases
• Curated lists

An open-source Python framework for building ETL pipelines that feed Retrieval-Augmented Generation systems, with multi-tenancy, cloud-native deployment and job scheduling.

• RAG
• Data engineering

An autonomous AI pentesting tool that runs a staged, evidence-backed security audit of web apps and APIs across identity, injection, business-logic and configuration risks, for targets the user is authorized to test.

• Security

A 12-million-parameter transformer language model implemented in Node.js and trained with the mni-ml/framework library on BPE-tokenized text such as TinyStories or YouTube-Commons transcripts.

• Models

A deep learning tensor library written from scratch in pure C, with autograd, GPT-style transformer building blocks, and CPU-only SIMD-accelerated training with no external ML dependencies.

• Models

A Model Context Protocol server that bridges AI coding assistants such as Claude Code, Cursor and Windsurf with a JetBrains TeamCity server, exposing build triggers, logs, test failures and configuration management as MCP tools.

• MCP servers
• CI/CD

A single-binary code intelligence tool that builds a persistent, source-grounded knowledge graph of a repository, so a coding assistant can look up dependencies, predict change impact, select relevant tests and verify refactors without rediscovering the codebase each session.

• MCP servers
• Agent memory

A local, offline prompt-engineering studio that turns rough ideas into structured prompts using self-hosted Gemma models through Ollama, with no cloud API, account or network access required after setup.

• Inference

A QuickStart deployment that lets a team experiment with retrieval-augmented generation in a chat interface, uploading documents, tuning sampling parameters and switching between simple and agent-based RAG.

• RAG

A distributed, peer-to-peer network for LLM inference where every peer both serves and consumes completions, metered by a BitTorrent-style upload-to-download ratio instead of money, brokered by a coordinator that never sees the request content.

• Inference

A Kubernetes-native orchestration platform for AI agents: a YAML Task runs a model call, a coding agent such as Codex or Claude Code, or a plain container command in an isolated pod, with the model keys staying inside the cluster.

• Agent frameworks
• Containers

A headless orchestrator for coding-agent CLIs that processes a shared work queue in deterministic order, dispatching each item to an adapter such as Claude Code, OpenCode, Codex or Aider and handling every outcome through an explicit path.

• Coding agents

An aggregating Model Context Protocol server that exposes every MCP server an organization runs through one authenticated endpoint, with meta-tool discovery, OAuth 2.1 single sign-on and Kubernetes custom resources.

• MCP servers

A curated index of over 570 publicly disclosed CVEs affecting the Model Context Protocol ecosystem, mapped to the OWASP MCP Top 10 risk categories for MCP servers, SDKs, gateways and clients.

• MCP servers
• Security

A deterministic Python parser for Logseq graphs that preserves the outliner's parent-child hierarchy when exporting Markdown for retrieval-augmented generation, alongside an interactive visualizer and an append-only writer.

• RAG

A terminal UI around llama.cpp for running, managing and benchmarking local GGUF models, with a setup wizard tuned for iGPU-class hardware and a launcher for the pi coding agent against the local server.

• Inference

A Visual Studio 2022/2026 extension that adds a local or cloud AI chat assistant with agentic capabilities, able to edit code, run builds and tests, and apply changes inside the IDE with tracked, reversible edits.

• Editors

A command-line tool that generates publication-quality LLM architecture diagrams directly from a model's config.json, computing parameter counts and VRAM footprints from the config rather than scraping them from a model card.

• Design tools

A Claude Code plugin that adds a self-learning autonomous agent system of 36 specialized subagents across four tiers, plus skills and slash commands for planning, implementing, reviewing and validating work automatically.

• Agent skills

A Spanish-language course repository covering AI and prompt engineering fundamentals, from large language models and prompt patterns to multimedia generation and an introduction to machine learning ethics.

• Tutorials

A browser-based and command-line calculator that estimates VRAM and RAM requirements for a GGUF model hosted on Hugging Face, without downloading the model.

• Inference

A Streamlit interface for a companion research project that explores whether autonomous AI agents can collaborate as a team to build a web application from scratch.

• Agent frameworks

A local MCP bridge server that lets a ChatGPT Web Pro session call tools on the user's own machine, reading and writing files, running shell commands and git, so ChatGPT can work the way the Codex coding agent does.

• MCP servers