Discover the Best AI Resources
Curated essentials, no noise — just what matters
AI Video2025
Retrieval-augmented generation framework for videos spanning hundreds of hours, runnable on a single RTX 3090. Builds multi-modal knowledge graphs over visual and audio content so you can query and chat across many long videos at once.
AI Agent2025
Lets you build, generate, and run multi-agent LLM workflows from natural-language prompts with no coding. Automatically profiles agents, creates tools/workflows, and supports multiple LLM providers plus CLI/Docker deployment.
Explains how modern LLMs are trained, tokenized, post-trained, and used, from internet-scale pretraining to RLHF and tool use. The value is a coherent mental model, not a quick product tutorial.
AI Audio2025
Provides real-time, local audio recording and transcription on macOS using Whisper and Parakeet engines, with global hotkeys and hold-to-record behavior. Includes model download, microphone selection, drag-and-drop file transcription, multilingual auto-detection and Asian-language autocorrect; Apple Silicon only.
AI Coding2025
Structures AI-assisted development as deterministic YAML workflows—planning, implementation, validation, review, and PR creation—so agent runs are repeatable and isolated. Mixes deterministic nodes with AI nodes and runs from CLI, Web UI, or chat integrations.
MCP Server2025
Runs a self-hosted meeting bot and transcription API that joins Google Meet, Teams and Zoom and streams speaker-attributed transcripts in real time. Compiles meetings into a git-backed Markdown workspace and runs sandboxed agents on your infrastructure; Apache-2.0 and air-gap capable.
AI Client2025
Performs automated, citation-backed deep research across web, arXiv, PubMed and your private documents using configurable local or cloud LLMs. Runs locally with per-user SQLCipher encryption, Docker/pip installs, LangChain integrations, and an MCP server for assistant integration.
AI Dataset2025
A curated dataset of ~30,000 CUDA kernels generated by an agentic pipeline, including reference PyTorch implementations, runtime metrics, NCU/Torch/Clang-Tidy profiles, error messages and correctness labels — released under CC-BY-4.0 for model fine-tuning and offline RL/optimization research.
AI Client2025
Optimizes and tests AI prompts in the browser, comparing original and rewritten versions side by side against any connected model. Runs fully client-side—keys go straight to the provider—and ships as web app, Chrome extension, and desktop builds.
AI Infra2025
High-performance CUDA tensor-core GEMM kernel library for LLM workloads: supports FP8/FP4/BF16, fused Mega MoE and MQA scoring, and runtime JIT-compiled kernels. Targets NVIDIA SM90/SM100 and PyTorch—for teams working on low-level GPU kernel optimization.
MCP Server2025
Feeds simplified Figma layout and style metadata to AI coding agents like Cursor and Claude Code to implement designs in one shot. Sends descriptive JSON (1px border, 16px padding) rather than code, leaving framework choices to the model.