Discover the Best AI Resources
Curated essentials, no noise — just what matters
Parses local AI coding-assistant session logs and presents a privacy-first dashboard that surfaces practice scores, anti-patterns, code-output metrics, skill discovery, and context-health checks. Runs as a VS Code extension or a GitHub Copilot canvas; requires building/installing the VSIX.
A small image-folder dataset for multimodal/vision model safety benchmarking, containing under 1,000 curated images with annotations to exercise safety-related model behaviours; licensed CC BY 4.0 and hosted on HuggingFace.
A reasoning-enhanced Mixture-of-Experts (MoE) LLM fine-tuned for multimodal image-text-to-text tasks and long-context reasoning; built on Qwen3.6-35B-A3B with LoRA and released as an experimental GGUF community model.
Provides JSON traces from a Codex-driven swebenchpro agentic benchmark, including per-call token counts, cache hit rates, timing, and per-trial outcomes. Useful for research into LLM caching, long-context workloads, and agent evaluation. MIT-licensed and compact.
Provides task-card metadata for 147 long-horizon professional tasks from the Agents Last Exam benchmark — titles, prompts, taxonomy, and input-file descriptors. This v1.0 release is metadata-only; companion repos host input files and gated reference outputs.
Trains one model to delegate work recursively to copies of itself. Joint reinforcement learning teaches task splitting and communication, improving harder-task generalization while trading extra computation for parallel execution.
Provides 10k–100k Indonesian-language cooking recipes in Parquet format, including dish names, ingredients and instructions — suitable for text-generation, recipe parsing, and culinary data analysis. Check the dataset card for license and field details.
Provides 1,781 OpenTelemetry execution traces of LLM-powered agents across six benchmarks, including full conversations, token usage, timing, tool calls and model metadata—useful for performance analysis, agent-behavior research, and inference debugging.
Open egocentric multimodal dataset for embodied AI and robot learning captured on commodity iPhone Pro: ~200 hours and ~10M RGB frames with LiDAR depth, ARKit 6‑DoF poses, IMU, two‑hand MANO mocap, room meshes, and hierarchical action captions.
Provides 173M DNA/RNA sequences (≈1.1 trillion nucleotides) assembled specifically for pretraining genomic foundation models. Includes eukaryote, prokaryote, and mRNA configs plus a 10B‑token eukaryote subset for faster experiments; formatted for streaming and tokenized with Carbon's 6‑mer setup.
Runs coding and long-running research workflows inside a persistent IPython environment with programmatic subagents and a durable 'Continual Harness' for session-level refinements. Key features include recursive subagents (RLM), executable Python skills, background daemon sessions, and evidence-backed local refinements. Best for reproducible, long-horizon coding, experiments, and evaluation pipelines where auditable agent-driven updates matter.
Diagnoses physical plausibility in generated videos by scoring adherence to 13 observable laws. It pairs benchmark prompts and model outputs with quality-controlled human ratings for fine-grained evaluation.