phuaky

Astra / GPT-6: 440 reported projects and workflows

Full corpus snapshot: 16 September 2026 at 08:44 Singapore time. Selected additions: 5 October 2026. The newer feed has not been exhaustively reviewed.

440 reported projects and workflows · 520 unique source posts. This list matches the current Astra Atlas.

The October additions are an MRI-to-printed-brain workflow, physical robot whip cracking and lassoing, AutoJev’s mixed-model training swarm, original sound effects for a muted edit, and Meshy’s interactive furniture catalogue. This update also carries over the September 16 additions and Branch, which were already in the atlas but absent from this gist.

These are creator reports, prototypes, and demonstrated workflows. They are not independently verified successes or production deployments. Mixed-model contributions, human input, and evidence limits remain in each summary. Identifiable same-project follow-ups are grouped.

bearlike

#!/usr/bin/env bash
# codex-init-mcp.sh
#
# Purpose
# -------
# Minimal, universal bootstrap for the "Remote MCP Client" (remote-mcp-cli via uvx).
# Intended for Codex init scripts and any repo/workdir (repo-agnostic).
#
# What it does
# ------------

bearlike

Below is an example of a tool that can be used with the OpenWebUI LLM. You must understand how the below code works and create a new well-documented tool that provides the desired functionality based on the new user requirement. Functions in the Tools class are exposed to LLM for tool selection. Functions in the Utils class are not exposed to LLM and are meant to be used as development helper functions. The EventEmitter class is used to emit events to the OpenWebUI. The Valves class is used to define the user configuration parameters for the tool. The some_functionality_exposed_to_LLM function is an example of a function that is exposed to the LLM. The some_helper_function_not_exposed_to_LLM function is an example of a function that is not exposed to the LLM. The main function is an example of how to run the tool locally. The main function is not exposed to the LLM. Each function in Tools represents a new exposed function to the LLM. There can be many functions in Tools available for LLM f

bearlike

"""
title: Explore Torrents managed by my qBittorrent Instance. Tool for OpenWebUI
author: KK
funding_url: https://github.com/bearlike
version: 0.1.3
license: MIT
"""

from qbittorrent import Client
from pydantic import BaseModel, Field

Diegiwg

LinkedIn

Search Jobs

The API URL for searching jobs is: https://www.linkedin.com/jobs-guest/jobs/api/seeMoreJobPostings/search, and it can be called this way, returning jobs from all categories.

Parameters

Parameter	Description

akaanirban

Edit 04/11/2021: This gist is quite old now. The current version of PyTorch is 1.8.1, which is miles ahead of version 1.0.1 that I was trying to install when I wrote this gist. Therefore some of the instructions may not apply, or some dependencies may have changed or bugs taken care of. I do not currently have a Raspberry Pi to verify unfortunately. Please proceed with caution. Further, there are may others who have shared their fixes, and direct links to their wheels down in the comments. Cheers !

Install the prerequisites (the last one for numpy):

sudo apt install libopenblas-dev libblas-dev m4 cmake cython python3-yaml libatlas-base-dev

Increase the swap size:

• Stop the swap : sudo dphys-swapfile swapoff
• Modify the size of the swap by editing as root the following file : /etc/dphys-swapfile. Modify the valiable CONF_SWAPSIZE and change its value to CONF_SWAPSIZE=2048

ruario

The included script 'widevine-flash_armhf.sh' fetches a ChromeOS image for ARM and extracts the Widevine binary, saving it in a compressed archive. Since it downloads a fairly large file (2Gb+ on disk after download) it is recommended that you run the script on a machine that has plenty of disk space.

To install the resultant archive, issue the following on your ARM machine–after copying over the archive if needed:

sudo tar Cfx / widevine-flash-20200124_armhf.tgz

(Where 'widevine-flash-20200124_armhf.tgz' is updated to reflect the actual name of the created archive)

tycho

These are the deltas required for the python.props file to build for ARM64 on Windows. You still need to add
the ARM64 platform definitions to the solution/project files before you can build, though.

diff --git a/PCbuild/python.props b/PCbuild/python.props
index 16a7672315..d865c86211 100644
--- a/PCbuild/python.props
+++ b/PCbuild/python.props
@@ -74,7 +74,8 @@
     -->
     <_RegistryVersion>$(Registry:HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Microsoft SDKs\Windows\v10.0@ProductVersion)</_RegistryVersion>

saurabhwahile

#You'll still have to manually enter dates here, as the xlsx file from zerodha does not show dates(SIP of stocks causes multiple dates)
#EDIT: Usage python zerodha_to_moneycontrol.py <FILENAME>
import sys
from openpyxl import load_workbook

wb = load_workbook(sys.argv[1])
ws = wb.active

csv_list = [["BSE/NSE/ISIN Code","Buy Date","Buy Quantity","Buy Price",]]

byrnedo

#!/bin/bash
# ensure running bash
if ! [ -n "$BASH_VERSION" ];then
    echo "this is not bash, calling self with bash....";
    SCRIPT=$(readlink -f "$0")
    /bin/bash $SCRIPT
    exit;
fi