Skip to content

Popular repositories Loading

  1. openfang openfang Public

    Open-source Agent Operating System

    Rust 16.1k 2k

  2. picolm picolm Public

    Run a 1-billion parameter LLM on a $10 board with 256MB RAM

    C 1.5k 176

  3. autokernel autokernel Public

    Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

    Python 893 78

  4. rightnow-cli rightnow-cli Public

    Claude Code for CUDA. Free AI assistant that actually understands GPU architecture

    Python 100 20

  5. qwen3.5-triton qwen3.5-triton Public

    Pure Triton kernels for Qwen3.5-27B inference on NVIDIA B200

    Python 92 9

  6. RightNow-GPU-Database RightNow-GPU-Database Public

    Comprehensive GPU specifications database with 2,824 GPUs across NVIDIA, AMD, and Intel

    70 13

Repositories

Showing 10 of 14 repositories
  • hclsm Public

    Hierarchical Causal Latent State Machines for Object-Centric World Modeling

    RightNow-AI/hclsm’s past year of commit activity
    Python 2 Apache-2.0 0 0 0 Updated Mar 31, 2026
  • openfang Public

    Open-source Agent Operating System

    RightNow-AI/openfang’s past year of commit activity
    Rust 16,056 Apache-2.0 1,993 75 34 Updated Mar 31, 2026
  • autokernel Public

    Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

    RightNow-AI/autokernel’s past year of commit activity
    Python 893 MIT 78 4 1 Updated Mar 19, 2026
  • TIDE Public

    Dynamic per-token early exit for LLM inference. Skip layers tokens don't need

    RightNow-AI/TIDE’s past year of commit activity
    Python 3 Apache-2.0 2 0 0 Updated Mar 18, 2026
  • qwen3.5-triton Public

    Pure Triton kernels for Qwen3.5-27B inference on NVIDIA B200

    RightNow-AI/qwen3.5-triton’s past year of commit activity
    Python 92 MIT 9 0 0 Updated Feb 28, 2026
  • picolm Public

    Run a 1-billion parameter LLM on a $10 board with 256MB RAM

    RightNow-AI/picolm’s past year of commit activity
    C 1,461 MIT 176 12 7 Updated Feb 22, 2026
  • forge-mcp-server Public

    Forge: Swarm Agents That Turn Slow PyTorch Into Fast CUDA/Triton Kernels

    RightNow-AI/forge-mcp-server’s past year of commit activity
    TypeScript 12 MIT 2 0 0 Updated Jan 30, 2026
  • tiny-tpu Public

    Minimal TPU implementation with 8x8 systolic array and PyTorch integration

    RightNow-AI/tiny-tpu’s past year of commit activity
    Python 57 MIT 5 0 0 Updated Jan 26, 2026
  • gpuci Public

    GPU CI/CD tool that tests CUDA kernels across multiple GPUs in parallel - Part of RightNow

    RightNow-AI/gpuci’s past year of commit activity
    Python 15 0 0 0 Updated Jan 25, 2026
  • RightNow-GPU-Database Public

    Comprehensive GPU specifications database with 2,824 GPUs across NVIDIA, AMD, and Intel

    RightNow-AI/RightNow-GPU-Database’s past year of commit activity
    70 Apache-2.0 13 2 0 Updated Jan 7, 2026