AI Agents Resources
A curated collection of tools, libraries, platforms and learning materials to help you design, build, orchestrate and manage autonomous AI agents and agentic workflows.
AI Agents Resources
A curated collection of tools, libraries, platforms and learning materials to help you design, build, orchestrate and manage autonomous AI agents and agentic workflows.
What’s under the hood?
Trained on NVIDIA’s Granary dataset: 120K hours of transcribed and pseudo-labeled English audio (LibriSpeech, Common Voice, YouTube-Commons, Librilight).
Handles punctuation, capitalization, and word-level timestamps out of the box.
Can run on systems with just 2GB of RAM, which makes it edge-device friendly—even if you’re not rocking a DGX box.
NVIDIA’s opening up the dataset post-Interspeech 2025, adding more transparency to the pipeline.
An open-source framework for building applications powered by large language models.
An open-source, low-code workflow automation tool that lets you visually design, orchestrate and run integrations between apps, APIs and databases—self-hosted or in the cloud.
An open-source, end-to-end platform for building, deploying and self-hosting LLM-powered applications
A lean, lightning-fast Python framework built entirely from scratch—completely independent of LangChain or other agent frameworks.
A low-code visual builder for LLM-powered applications
A Python agent framework designed to make it less painful to build production grade applications with Generative AI.