Explore the directory

A Terraform-style command-line tool for running teams of AI coding agents such as Claude Code, Codex and Aider, defining roles and workflows in a config file so intake, implementation, review, CI and merge happen as repeatable operations.

• Coding agents
• CI/CD

A collection of Chinese-language example projects for prompt engineering, LLM applications, RAG and agents, spanning older LangChain 0.1 code and newer LangChain and LangGraph 1.0 examples covering middleware, structured output and workflows.

• Tutorials

A spreadsheet framework built for coding agents: a model is written as React components, and open-sheet resolves cell addressing, formula references and recalculation and exports a live, working .xlsx file that recalculates when a value changes.

• Libraries

An unofficial project that runs Japan's Digital Agency GENAI government AI entirely locally, replacing cloud dependencies with SAML authentication through Keycloak, an OpenAI-compatible backend, RAG through Qdrant, and local transcription and image generation.

• RAG
• Inference

A high-performance Rust proxy that queues requests from multiple users in front of one or more Ollama or LM Studio instances, dispatching them in parallel with a least-connections, round-robin, model-aware scheduler and a real-time terminal dashboard.

• Inference
• LLM gateways

An AI-native distributed data plane in Rust that unifies high-performance RPC, KV cache sharing, an elastic message queue and S3-compatible file acceleration behind three standardized interfaces, aimed at AI training and inference bottlenecks.

• Inference
• Data engineering

A FastAPI and Vue local web UI wrapper around the DeepSeek-OCR model, letting a user upload a PDF or image, watch inference progress, and inspect the extracted text with bounding-box overlays, including math formulas and tables.

• Inference

A source-code generation framework that borrows ideas from JavaScript UI frameworks such as React and Solid, letting a generator describe source files and their contents using JSX or string templates.

• Libraries

A KEDA external scaler that reads GPU utilization and memory directly from NVIDIA's NVML library through a DaemonSet, so Kubernetes can autoscale GPU inference workloads without Prometheus or DCGM.

• Containers
• Monitoring

A tool that reverse-engineers a large or unfamiliar codebase into an end-to-end map of business workflows, connected code and evidence-backed risks, run from the command line against a local repository path with no API key required.

• Code quality

A production-ready Next.js template for building AI agents with LangGraph.js, featuring dynamic Model Context Protocol tool loading from a web UI, human-in-the-loop tool approval, persistent PostgreSQL-backed conversation memory, and real-time streaming responses.

• Agent frameworks

A snapshot-testing tool for AI agents that records the tools an agent calls, in what order and with what output, then flags any drift from that recorded baseline in CI, working with LangGraph, CrewAI, OpenAI Assistants and Anthropic-based agents.

• AI evals
• Testing

A high-performance knowledge graph engine built for large language models and GraphRAG, using sparse matrix algebra for sub-millisecond graph traversals, with full OpenCypher query support and Python, JavaScript and Docker access.

• RAG
• Databases

The official Model Context Protocol server for Dart, an AI-powered project management tool, exposing prompts, resources and tools so an MCP client such as Claude Code or Cursor can create, list, update and comment on tasks and documents.

• MCP servers

Deployment scripts for running vLLM across one to many NVIDIA DGX Spark systems, connected directly by cable or through a switched fabric, with tensor parallelism that scales automatically with the cluster size and more than 40 tested model presets.

• Inference

A Google Cloud Platform sample that demonstrates real-time text semantic search end to end, extracting embeddings with the Universal Sentence Encoder and building an approximate nearest-neighbour index with the Annoy library.

• RAG

A self-hosted, Docker-first, OpenAI-compatible LLM gateway for local projects and private teams, giving every application one stable API endpoint and key while the gateway manages upstream provider accounts, credentials, two-lane fallback chains and usage limits.

• LLM gateways

An Open Knowledge Format wiki synthesized from one YouTuber's long-form catalog on agentic coding, AI engineering, RAG and memory systems, dropped next to any project so a coding agent can cite the exact video and timestamp behind an answer.

• Agent memory
• Tutorials

A memory layer for AI coding agents that indexes work across every repository a developer touches into one semantic graph, so an agent can check whether a problem was already solved elsewhere.

• Agent memory

A 25-language speech recognition model built from NVIDIA's Parakeet TDT 0.6B v3, replacing half its encoder's temporal filters with fitted, frozen Gabor kernels and retraining the rest, reporting lower error rates than Parakeet on most benchmarks.

• Models
• Speech

A Swift package for building on-device retrieval-augmented generation pipelines, combining a document-parsing library with a vector store and semantic search into one end-to-end pipeline for creating a searchable knowledge base on iOS or macOS.

• RAG

A Python framework that couples large-language-model reasoning with an evolutionary loop to automatically invent, mutate and benchmark optimization algorithms, with an in-the-loop hyperparameter-optimization mode and niching strategies to keep a diverse population of solutions.

• Agent frameworks

An open simulation stack for LLM and vision-language-model driven embodied agents in large 3D environments, combining a FastAPI and LangGraph backend with a Cesium-powered Unreal Engine 5.5 plugin for heterogeneous simulated vehicles, drones, robots and other actors.

• Agent frameworks

A property graph database for .NET that combines graph relationships, tags, labels, JSON data, and vector search in one persistence layer, with REST, MCP, and dashboard access.

• MCP servers
• Databases