Explore the directory

An autonomous Claude Code skill that packages MIPS R5900 architecture knowledge and PS2Recomp project conventions so an AI agent can reverse-engineer and recompile PlayStation 2 games with persistent memory across sessions.

• Agent skills

A CLI tool that collects and verifies free HTTP, SOCKS4, and SOCKS5 proxies from more than 700 public sources, filtering out honeypots and script-injecting proxies, with an optional rotating proxy server and an MCP server for AI agents.

• CLI tools
• Networking

A reference implementation of a permission-aware Agentic RAG system for enterprise document knowledge bases, enforcing folder-level access control through every step of retrieval, reranking, and citation.

• RAG
• Security

A Python MCP server that bridges AI coding assistants with the OpenTelemetry ecosystem, giving them live access to documentation, examples, semantic conventions, and instrumentation-quality scoring.

• MCP servers
• Monitoring

An open-source, AI-assisted network security scanner that runs 27 plugins to find and prioritize vulnerabilities, map them to CVEs and MITRE ATT&CK, and track changes across scans, entirely on the user's own machine.

• Security

A self-hosted, open-source monitoring platform that uses an LLM to analyze alerts, pick a runbook, and execute automated remediation, in addition to standard metrics and PromQL dashboards.

• Monitoring

A local inference server for Apple Silicon that hot-swaps MLX models on demand, loading one text, vision, embedding, TTS, STT, or decision model at a time behind an OpenAI-compatible API.

• Inference

A local image and video generation runtime for Apple Silicon and MLX, covering text and image-to-image, instruction-based editing, and text, image, and reference-to-video generation and restoration.

• Generative media

A single-binary Rust database purpose-built for AI agent workloads, combining a temporal knowledge graph, a relational table engine, and sandboxed WASM agents behind one query language.

• Agent memory
• Databases

An open-source Python framework for building multi-agent AI systems, with persistent memory, long-context management, tool integration, and both decentralized and hierarchical agent orchestration.

• Agent frameworks

An AI coding skill that generates and modifies Metin2 game-client UI code from screenshots, natural-language descriptions, or existing scripts, for Claude Code, Cursor, Codex, and other agents.

• Agent skills

A tool for running Hugging Face language models on Apple Silicon that are too large to fit in RAM, by streaming their weights layer by layer from disk, including large mixture-of-experts models.

• Inference

An MCP server that gives AI coding assistants deterministic knowledge of a project's actual AWS infrastructure and database schemas, instead of letting them guess from source code alone.

• MCP servers

An MCP server that connects Google Search Console to AI clients such as Claude Desktop, Cursor, and Codex CLI, so an assistant can read search performance and diagnose indexing issues.

• MCP servers

A CPU-first, eager-execution tensor and autograd library written in pure Zig, with compile-time-checked named tensor axes and no C/C++ or Python dependency.

• Inference
• Libraries

A Rust-native LLM serving engine, distributed as a single binary, that serves local models over an OpenAI-compatible API with no Python runtime needed.

• Inference

A lightweight Python framework for evaluating information-retrieval systems such as RAG and search pipelines, computing standard metrics like Hit Rate, Recall, NDCG, and MRR.

• RAG
• AI evals

An MCP server that gives AI coding assistants long-term memory across sessions and clients, storing architecture decisions and preferences once and recalling them through six retrieval strategies.

• MCP servers
• Agent memory

Two side-by-side sample RAG (Retrieval-Augmented Generation) projects for Korea's eGovFrame standard framework, one built with Spring AI and Redis Stack and the other with LangChain4j and PostgreSQL/pgvector.

• RAG
• Tutorials

Training material that shows how to deploy and run large language models on local infrastructure such as HPC systems, including a slide deck, source code, and model and data download scripts.

• Tutorials

An open-source command-line AI coding assistant powered by the DeepSeek-V3 model, positioned as a lower-cost alternative to proprietary coding-agent products.

• Coding agents

A pure Go SDK for Claude Code's agentic capabilities, tracking the official TypeScript Agent SDK, that manages the Claude Code CLI as a subprocess and communicates over line-delimited JSON.

• Agent frameworks

A modular reference implementation for building enterprise agents on SAP Business Technology Platform that integrate with SAP's Joule assistant over the A2A protocol and use the SAP-RPT-1 model as a forecasting tool.

• Agent frameworks

A curated index of AI agent frameworks, coding and automation agents, MCP servers, and evaluation tools for 2026, organized into categories such as agent frameworks, ethical hacking, OSINT, and local AI agents.

• Curated lists