Discover the Best AI Resources

NVIDIA NeMo Speech

Provides a toolkit and codebase for building, training, and deploying speech and multimodal models — Automatic Speech Recognition, Text-to-Speech, and speech-aware LLMs — with modular neural components and pre-trained checkpoints for PyTorch. Supports streaming/low-latency inference, multi-language models, and optional compiled kernels for acceleration.

Chatwoot

Consolidates customer conversations from website chat, email, social and messaging channels into a single support inbox with self-hosting and Docker/one-click deployment options. Includes an optional AI agent (Captain) for automated replies, multilingual translation, and integrations.

Detectron2

Modular implementations of object detection, instance/semantic/panoptic segmentation and related vision models for research and deployment. Offers a large model zoo, export to TorchScript/Caffe2, and PyTorch-native optimizations for faster training and extensibility.

Milvus

Runs approximate nearest-neighbor search over billions of vector embeddings, separating compute from storage so reads and writes scale independently. Offers HNSW, IVF, DiskANN, and GPU CAGRA indexes plus hybrid dense+sparse and BM25 retrieval.

Megatron-LM

Trains transformer models from 2B to 462B parameters across thousands of GPUs by combining tensor, pipeline, context, and expert parallelism. Ships composable building blocks (Megatron Core) plus reference scripts, with FP8/FP4 and ~47% MFU on H100s.

Supabase

Provides a hosted or self-hosted Postgres platform that exposes database, auth, realtime subscriptions, file storage, serverless functions, and auto-generated REST/GraphQL APIs. Includes an AI & vector/embeddings toolkit and modular client libraries for building web, mobile and AI applications without stitching multiple vendors.

Metaflow

Write ML, AI, and data science pipelines as plain Python, debug them locally, then deploy the same code to cloud compute and production orchestration unchanged. Handles dependency pinning, data versioning, and experiment tracking automatically per run.

Flyte

Orchestrates ML pipelines and agentic workflows authored in plain Python, no DSL required. Adds durable execution with automatic retries and crash recovery, infra-aware autoscaling, and caching so the same code runs locally and at production scale.

Demonstrated that language model loss falls as a smooth power law in model size, data, and compute across more than seven orders of magnitude — turning "make it bigger" from a hunch into a budget you can plan, and justifying the GPT-3 scale-up.

Career advice for ML researchers from the creator of TRPO and PPO: how to pick problems worth solving, why goal-driven beats idea-driven research, and the daily notebook-and-review habit that compounds small experiments into breakthroughs.

Tianshou

Deep reinforcement learning library on pure PyTorch and Gymnasium, with 30+ algorithms across on-policy, off-policy, and offline RL. Exposes both a one-call high-level interface and a procedural API, plus vectorized envs and reproducible MuJoCo benchmarks.

Reactive Resume

Build, customize, and export professional resumes via a privacy-first web app with real-time preview and client-side PDF export. Offers templates, JSON/DOCX exports, Docker self-hosting, and optional AI-driven content suggestions.