Explore the directory

A collection of installable skills for AI coding agents covering code review, testing, design docs, debugging, security audits, refactoring and cleaning up AI-written text, distilled from public collections and real project practice.

• Agent skills

A curated, organized list of protocols and standards used by AI agents, covering MCP, A2A, ACP, AG-UI, AP2, x402 and more than 50 others, grouped by stack layer.

• Curated lists

A self-hostable AI hub for enterprise knowledge that combines hybrid retrieval-augmented generation, a typed knowledge graph and agentic tool use behind a Laravel platform, positioned as an on-premises alternative to hosted knowledge assistants.

• RAG

A hardware-agnostic LLM inference engine written in Rust that streams model weights layer by layer from NVMe storage, so a single consumer GPU can run large models that do not fit in its VRAM.

• Inference

A monitoring tool that watches the traffic between AI agents and tool calls to catch coordination failures a normal tracing tool misses, such as silent loops, repeated work, runaway subagent fan-out and hung or retrying tool calls.

• AI evals

A catalog of named integration patterns for multi-agent AI systems, written to give architects a shared vocabulary the way Enterprise Integration Patterns did for distributed systems.

• Agent frameworks
• Books

A production-minded, dependency-free server-side agent runtime in TypeScript that handles streaming chat, tool calling and knowledge-base retrieval with explicit, tested handling of edge cases like aborted runs and token-limit cutoffs.

• Agent frameworks

Pre-compiled, encrypted streaming speech-recognition model weights in VoxRT's .vxrt format, for consumption by the VoxRT on-device runtime on Android and iOS.

• Models
• Speech

A PyTorch Tree2Tree model that translates natural-language descriptions into source code by decoding a syntax tree of grammar rules instead of generating tokens one at a time.

• Models

A local-first CLI that packs a codebase into a compact, lossless, searchable archive that can be queried and restored byte-for-byte, for agent memory and local RAG.

• Agent memory
• RAG

A zero-shot keyword and keyphrase extraction library that reads keywords directly out of a pretrained language model's attention weights, no fine-tuning or labeling required.

• Libraries

An automatically updated, auto-categorized link collection of plugins for the herdr agent-session tool, organized by what a user wants to get done.

• Curated lists

A GPU hardware-abstraction layer for LLM inference fleets that gives hot failover between an active and standby domain at the cost of zero idle GPUs.

• Inference
• Hosting

Generates JAX-RS server stubs, Quarkus-optimized applications, data models and client libraries from OpenAPI specifications.

• APIs

A C# REPL library that can be embedded in any .NET application, with syntax highlighting, code completion and runtime type introspection.

• Languages
• Libraries

A CLI that turns a project folder into a GPU dev box, Jupyter session, hosted web app or LLM endpoint on Modal, showing the price per hour before anything starts.

• CLI tools
• Hosting

A Laravel package that provides a fluent, facade-based interface for managing collections and running vector similarity searches against a Qdrant database.

• Databases

A Chrome extension that connects to one or more Qdrant vector database clusters and shows cluster health, collection configuration, shard distribution and performance in real time.

• Databases
• Monitoring

A single-file, offline-first vector database for Rust that stores embeddings, source text and search indices in one verifiable, reproducible file with stable content-hash citations.

• Databases

A disk-backed vector database written in Rust that uses HNSW indexing and quantization for approximate nearest-neighbor search over embeddings.

• Databases

Node.js bindings for Zvec, an open-source, in-process vector database that embeds directly into applications for low-latency similarity search without a separate server.

• Databases

A full-stack web chat application that lets users switch between five language models, ask questions grounded in uploaded documents through retrieval-augmented generation, search the web in real time, and analyze images, with streaming responses.

• RAG
• Inference

A WordPress plugin that exposes 86 MCP abilities for posts, pages, comments, custom post types, menus, patterns, media, taxonomy, users, settings and plugin management, so AI agents can manage a WordPress site programmatically.

• MCP servers

A local retrieval-augmented-generation engine that fuses vector similarity, BM25 keyword search, knowledge-graph traversal and metadata filtering, running entirely on ONNX Runtime with no PyTorch or GPU required.

• MCP servers
• RAG