Explore the directory

A unified post-training and real-time inference framework for accelerated video generation, supporting full and LoRA fine-tuning, sparse attention and distillation techniques that cut denoising steps and GPU time.

• Models
• Generative media

A bio-inspired cognitive memory engine that scores retrieval by the strongest chain of reasoning connecting a query to an answer, instead of ranking by vector similarity or a static knowledge graph.

• Agent memory
• RAG

A local-first, self-hosted memory engine for LLM applications and agents, with durable SQLite storage, temporal and provenance tracking, and one TypeScript engine reachable from npm, a CLI, HTTP, MCP and VS Code.

• Agent memory

A command-line tool for semantic search over video footage: describe what you are looking for in text or an image, and it returns a trimmed clip from the matching moment.

• RAG

An alpha-stage tool that keeps one unit of work moving across different coding agents, such as Codex, Claude and OpenCode, so switching agents does not mean re-explaining context or losing progress.

• Coding agents

A Rust-native substrate for fast local decisions and persistent AI-agent memory, combining local semantic embeddings, vector retrieval, graph relationships and feedback-based learning without a database server or API key.

• Agent memory

An open-source registry and proxy that federates MCP, A2A and REST or gRPC APIs behind one endpoint, adding centralized governance, discovery, observability and plugin extensibility for AI infrastructure.

• MCP servers
• LLM gateways

The official C# SDK for the Model Context Protocol, maintained with Microsoft, letting .NET applications, services and libraries implement and interact with MCP clients and servers.

• MCP servers

A curated, multilingual list of resources, patterns and templates for harness engineering: the scaffolding of context delivery, tool interfaces, planning artifacts, verification loops and memory that surrounds an AI agent.

• Curated lists

A Python library and runnable textbook packaging 35 production-grade agentic AI patterns, such as Reflexion, LATS, GraphRAG and MemGPT, each with an executed notebook, multi-provider support and a shared benchmark leaderboard.

• Agent frameworks
• Tutorials

An Android library, forked from Chuck, that inspects HTTP and HTTPS traffic made through OkHttp, recording every request and response for review inside the app.

• Debugging

An open-source command-line tool that compiles raw documents into a structured, interlinked wiki-style knowledge base using large language models, with reasoning-based retrieval for long documents and no vector database required.

• Agent memory
• RAG

An agent-native operating system for robotics that lets a developer command humanoids, quadrupeds, drones and other hardware in natural language and build multi-agent systems using camera, lidar and actuator input, without ROS.

• Agent frameworks

A Python framework, built on the OpenAI Agents SDK, for orchestrating multi-agent applications by modeling an organization's roles, such as CEO, developer and assistant, as communicating agents.

• Agent frameworks

A JVM framework, in idiomatic Kotlin and Java, for building AI agents that call tools, run multi-step workflows and communicate with users across backend services, Android, iOS and browser environments.

• Agent frameworks

A single-package Retrieval-Augmented Generation platform, built on Langflow, Docling and OpenSearch, that lets users upload documents and query them through a chat interface with agentic, multi-agent workflows.

• RAG

A repository of Google's official Model Context Protocol servers, covering both hosted remote servers and open-source servers, along with guidance for deploying MCP servers to Google Cloud.

• MCP servers

A Chinese-language PyTorch tutorial, in a second edition, covering PyTorch fundamentals, computer vision, NLP and large-model applications, plus inference deployment with ONNX and TensorRT and companion example code.

• Tutorials

A multi-language Vulkan, OpenGL, GLES, EGL, GLX, and WGL loader-generator based on the official specifications, with a web service that generates the loader files a project needs.

• Libraries

A C++ library for low-latency machine code generation, providing backend-independent core APIs plus x86, x64, and AArch64-specific assemblers and a higher-level compiler.

• Libraries

A self-hosted infrastructure layer built around one database and one AI gateway, so every AI assistant a person uses shares the same persistent memory instead of keeping separate, disconnected histories.

• Agent memory
• Databases

An open-source reinforcement-learning infrastructure for embodied and agentic AI, used to train robotics and vision-language-action models at scale with GRPO and other RL algorithms.

• Models

A production-ready REST and Model Context Protocol API layer for an existing or new PostgreSQL database, adding CRUD, custom SQL routes, authentication, and access control without writing backend code.

• APIs
• Databases

A Codex instruction installer that previews changes before writing them, deploys a versioned instruction set into Codex without touching its software or credentials, and can be fully reverted.

• Agent skills
• CLI tools