General-Instinct/InstinctFlash

High-Performance Serving Runtime for Robotics Models

Hardware, IoT & roboticsC++

2.0 Steady Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of September 22, 2026, 18:43 UTC.

Open on Seismograph Open on GitHub

About the project

A high-performance serving runtime for robotics models (VLA, WAM, policies) with FP8 acceleration and optimized kernels on Jetson Thor and RTX 4090/5090.

Useful for

Serve a fine-tuned robotics checkpoint for inference via `instinctflash serve`
Expose robot action predictions over the openpi WebSocket protocol to existing clients
Speed up pi0.5 or LingBot-VA inference with FP8 on Jetson Thor

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

10 stars so far today, about 12 expected by the end of the day. The usual pace is 0 per day, so that's 12× as much.
Hacker News: “Show HN: InstinctFlash – Run 5B world-action models in real time on Jetson Thor” — 10 points, 3 h ago.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 21
Today: 10 · ≈ 12 by evening
Forks: 5
Issues and pull requests: 11
Watchers: 0
Language: C++
License: AGPL-3.0
Latest release: thor-2026-09-15 · September 15, 2026
Created: May 28, 2026
Last push: September 18, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Hacker News discussions

Show HN: InstinctFlash – Run 5B world-action models in real time on Jetson Thor10 points, September 22, 2026

Spotted in

September 22, 2026Spotted on Hacker News

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/General-Instinct/InstinctFlash.svg?lang=en)](https://gitnova.dev/en/r/General-Instinct/InstinctFlash)

Similar by description

0.0
joykraft/vla_pi0
Project for the Episode1 single-arm robot: teleoperation data collection via LeRobot, LoRA fine-tuning of the π₀ (pi0) VLA model on OpenPI/JAX, and deployment of the policy to a real robot over WebSocket.

SteadyHardware, IoT & roboticsPython+0 stars today, ≈ 0 by evening
1.5
NVIDIA/TensorRT-LLM
NVIDIA library for optimizing inference of large language models and visual generative models on GPUs, with a Python API, specialized kernels, and an efficient C++/Python runtime.

SteadyLanguage modelsPython+8 stars today, ≈ 10 by evening
1.3
microsoft/onnxruntime
Cross-platform accelerator for ML inference and training. Runs models from PyTorch, TensorFlow, scikit-learn and others via the ONNX format with graph optimizations and hardware acceleration.

SteadyLanguage modelsC+++3 stars today, ≈ 4 by evening
0.0
Binaire-0101/FRZi-inference
FRZi-inference is an inference engine for running machine learning models. It is designed to execute pre-trained models and obtain predictions.

SteadyLanguage models+0 stars today, ≈ 0 by evening