Discover the Best AI Resources

modded-nanogpt

A community speedrun to train a 124M GPT as fast as possible on 8 H100s, all chasing a fixed 3.28 FineWeb loss. Successive records cut the run from llm.c's 45 minutes to under 1.4, mostly via the new Muon optimizer rather than more hardware.

goose

Runs local AI-agent workflows through a desktop app, CLI, and embeddable API, connecting many LLM providers and MCP extensions for editing, execution, testing, and automation.

OmniParse

Ingests documents, images, audio, video and web pages and converts them into structured, LLM-friendly markdown and parsed data. Runs locally (fits on a T4 GPU), supports ~20 file types, offers OCR, transcription, table extraction and a Gradio UI; deployable via Docker/Skypilot. Licensed under GPL-3.0; some model weights carry cc-by-nc-sa restrictions for commercial use.

Data Formulator

Combines drag-and-drop field binding with natural-language prompts so an AI agent derives the transformations behind charts your raw tables can't produce. Reads from databases, files, images, and websites; 30+ chart types and branchable threads.

AIBrix

Cloud-native control plane that scales vLLM on Kubernetes, adding the routing, autoscaling, and fault tolerance single-instance serving lacks. Brings high-density LoRA management, an LLM gateway, distributed KV cache reuse, and SLO-aware GPU serving.

Tambo AI

Register React components with Zod schemas so an LLM agent can select, fill, and stream their props from user requests, turning chat into live interactive UI. Works with OpenAI, Anthropic, Gemini, and Mistral, plus MCP servers like Linear.

screenpipe

Continuously records your screen and audio 24/7 to a local, searchable timeline you can query in natural language. Stores screenshots with accessibility data in SQLite, and a plugin system runs scheduled AI agents on what it captures.

A 236B-parameter Mixture-of-Experts LLM that activates only 21B parameters per token, cutting training cost 42.5% versus a dense 67B model and shrinking the KV cache 93.3% via Multi-head Latent Attention, with 128K context.

TEN-framework/ten-framework

Builds real-time multimodal conversational AI agents with voice-assistant examples, VAD, turn detection, RTC/WebSocket transport, avatars, transcription, and edge-device demos.

Pydantic AI

Provides a Python framework for building generative-AI agents and workflows with Pydantic-style type safety and composable capabilities. Model-agnostic provider support, built-in observability, human-in-the-loop tool approval, and durable execution for production use cases.

hf-audio/open-asr-leaderboard

Provides leaderboard-ready test splits for the Open ASR Leaderboard: converts unsafe custom loaders to Parquet, sorts samples by audio length, and packages eight ESB test sets (LibriSpeech, Common Voice, GigaSpeech, SPGISpeech, etc.) for reproducible ASR benchmarking.

exo

Connects multiple Macs and Linux machines into one cluster to run models too large for any single machine. Auto-discovers peers, shards a model across them via tensor parallelism, and exposes OpenAI-, Claude-, and Ollama-compatible APIs.