Explore the directory

A curated list of resources for natural language processing, covering linguistic analysis, multilingual tooling, classical and neural methods, libraries by programming language, datasets and evaluation benchmarks.

• Curated lists

An open, continually updated book of methodologies, tools and step-by-step instructions for training and fine-tuning large language and multi-modal models, aimed at the engineers and operators who run that training.

• Books

An open agent framework that gives an AI agent a full Dockerized Linux desktop, a browser with DOM annotation, and live document editing, so it can use real GUI software and files rather than only chat.

• Agent frameworks

A Python framework for computing, using and training embedding and reranking models, including sentence embeddings, cross-encoder reranking, sparse embeddings and ColBERT-style multi-vector retrieval, for semantic search and similarity tasks.

• RAG
• Models

An in-browser large language model inference engine that runs open source models directly in a web browser using WebGPU acceleration, with an API compatible with OpenAI's.

• Inference

A library for post-training foundation language models with reinforcement learning and preference optimization methods, such as supervised fine-tuning, GRPO and DPO, built on top of Hugging Face Transformers.

• Models

An unofficial Python API and agent skill for Google's Gemini Notebook (formerly NotebookLM), giving programmatic access to research automation, content generation and file exports from Python, a CLI, or AI agents such as Claude Code and Codex.

• Agent skills
• Libraries

An open-source TypeScript framework and product stack for autonomous AI agents, including a runtime, a user-facing app for web, desktop and mobile, a CLI, cloud services and native bridges.

• Agent frameworks

A framework for running and fine-tuning large language models through CPU-GPU heterogeneous computing, letting large mixture-of-experts models do inference and LoRA fine-tuning on consumer hardware with CPU expert offload.

• Models
• Inference

An interactive, beginner tutorial that teaches AI-native "vibe coding", building software by describing what is wanted, through step-by-step visual lessons, a simulated coding environment and hands-on exercises, translated into ten languages.

• Tutorials

An AI coding agent skill that uses workplace performance-improvement-plan rhetoric to push a coding agent to keep trying different approaches and follow a debugging checklist instead of giving up early.

• Agent skills

An AI research assistant that performs iterative, deep research on a topic by combining web search, scraping and large language models, refining its research direction between iterations and compiling a sourced markdown report.

• Agent frameworks
• Browser automation

A cross-platform desktop application that has a language model read imported documents and incrementally build and maintain a structured, interlinked wiki, instead of answering from scratch with retrieval-augmented generation each time.

• Agent memory
• Documentation tools

An open-source agentic AI assistant that connects to databases, spreadsheets and knowledge bases, writes SQL and code from natural language questions, and turns the results into charts, dashboards and reports.

• Databases
• Data engineering

A multi-agent framework built on the CAMEL-AI framework for automating real-world tasks, coordinating several AI agents that use tools such as browsers and MCP servers to complete work.

• Agent frameworks

An agent framework that lets a language model of choice autonomously use tools to fix issues in real GitHub repositories, solve offensive cybersecurity challenges, or complete other custom coding tasks.

• Coding agents
• Agent frameworks

A terminal-based AI coding agent harness built for low RAM usage, with published benchmarks comparing its memory footprint to other coding-agent CLIs.

• Coding agents

A typed Python SDK for building AI agents that can run behind a web frontend, in a terminal, on a voice call or as a background job, with the same agent portable across models and interfaces.

• Agent frameworks

A self-hosted REST API, MCP server, and web console for fetching Douyin and TikTok posts, profiles, comments, and search results, and downloading their video and image content.

• APIs

A collection of Agent Skills for Google Cloud and other Google products, installable into AI coding agents, covering onboarding, authentication, Kubernetes administration, BigQuery, Genkit, the Gemini API and multi-product solution architectures.

• Agent skills

Two open-weight language models from OpenAI, gpt-oss-120b and gpt-oss-20b, designed for reasoning and agentic tasks such as function calling, web browsing and code execution, released under the Apache 2.0 license.

• Models

A free knowledge hub about AI tools for programmers, with product introductions, usage guides, reviews, tips, application examples, monetization advice, industry news and a beginner course on building software by describing it to an AI.

• Tutorials
• Curated lists

An industrial speech recognition toolkit for training and running offline, streaming and edge automatic speech recognition, voice activity detection, punctuation restoration and speaker diarization models, with OpenAI-compatible and MCP serving.

• Speech

A pure Go library for reading and writing Microsoft Excel spreadsheet files, including charts, images and a streaming API for large datasets.

• Libraries