📦 lihanyu81/polymarket_lp_tool

Automate Polymarket Liquidity Provisioning with Rust and Python

Manage and adjust your Polymarket limit orders automatically with a toolkit designed for liquidity providers. This repository offers a Python-based reference implementation alongside a high-performance Rust rewrite that handles real-time market data through WebSockets. The system monitors your open orders and applies custom pricing strategies, such as coarse or fine tick adjustments, while integrating anti-sniping protections like mid-price filtering and post-fill cooldowns. Users can interact with the bot through Telegram commands or a web interface to set specific rules per token. Start with small exposure to refine your automated trading strategy and maintain reliable market presence.

🆔 @hackernewsgithubprojects

📦 strongca22-cpu/gabagool

Automate Polymarket Arbitrage with Gabagool

Gabagool is a hybrid Polymarket arbitrage trading bot designed to lock in guaranteed profits by simultaneously buying underpriced YES and NO shares. By integrating proven components like thread-safe position tracking, automated settlement, and gas-efficient position merging, the bot identifies and executes trades when the combined cost falls below one dollar. It targets fifteen-minute markets for assets like Bitcoin, Ethereum, and Solana to capture consistent margins. This project streamlines trade validation and risk management through a structured, modular approach, making it an effective tool for those looking to automate their market participation. Start testing your strategy today.

🆔 @hackernewsgithubprojects

📦 yangyuan-zhen/polyweather

PolyWeather: Institutional Weather Intelligence for Quant Markets

PolyWeather serves as a high-precision weather intelligence terminal specifically engineered for temperature-based settlement markets. This system monitors 51 global cities by blending real-time observations from aviation and meteorological networks with a proprietary Dynamic Error Balancing model to generate accurate temperature forecasts. It provides professional traders with detailed intraday analysis, including calibrated probability distributions and market-implied signal differences, all delivered through a real-time dashboard and Telegram alerts. By combining raw observation data with rigorous error correction, the platform helps users interpret complex weather trends and settlement risks more effectively. This specialized tool transforms raw meteorological data into actionable market context.

🆔 @hackernewsgithubprojects

📦 gwitko/conduit

Conduit: Privacy-Focused SSH and Mosh for Mobile

Manage your remote servers directly from your phone with a modern, privacy-focused client for Android and iOS. This tool enables you to run secure SSH and Mosh sessions, perfect for maintaining connections even when moving between cellular and Wi-Fi networks. It supports hardware keys, including USB and NFC authentication, and offers an integrated SFTP browser for seamless file management. Since everything is stored locally on your device with no cloud syncing or accounts required, your keys and host profiles stay private. With built-in themes and tmux integration, you can maintain a productive workspace anywhere you go.

📰 https://news.ycombinator.com/item?id=48582962

🆔 @hackernewsgithubprojects

📦 frkak/piyaz

Piyaz: The Agentic Workspace for Human-AI Collaboration

Piyaz functions as an agentic workspace that enables humans and AI coding agents to collaborate on software projects within a shared context network. Rather than forcing agents to start from zero in every session, Piyaz tracks project tasks, implementation plans, and context in a unified store that both developers and agents can access. This system uses plugins for major coding agents to handle project management, automate task decomposition, and orchestrate end-to-end workflows. By providing a persistent, readable map of project decisions and dependencies, it allows agents to walk into any session knowing exactly what to build next.

🆔 @hackernewsgithubprojects

📦 nox-project/nox-framework

Automate OSINT Intelligence Gathering with NOX

NOX is a high-performance cyber threat intelligence framework capable of scanning over one hundred and twenty sources simultaneously to automate identity pivoting and risk analysis. It functions as a plugin-driven engine that processes breach data, cracks passwords, and scrapes paste sites or social channels without manual intervention. By using a recursive avalanche approach, it automatically re-injects discovered identifiers as new seeds for deeper scanning while maintaining operational security through automatic proxy rotation. This tool is designed to provide actionable intelligence for security professionals, effectively streamlining complex forensic research into a single, cohesive command-line workflow for identity and exposure assessment.

🆔 @hackernewsgithubprojects

📦 sohamw03/wifui

Manage Windows Wi-Fi from your Terminal

Control your Windows network connections directly from the command line using this lightweight, keyboard-driven interface. Built with Rust, this tool lets you instantly scan for nearby networks, connect to secured or open Wi-Fi, and view detailed signal info without opening standard system menus. You can even generate QR codes to share your saved credentials with others efficiently. By using Vim-like keybindings, navigation becomes incredibly fast and intuitive for power users. It provides a clean, responsive way to handle wireless settings entirely within your terminal, making it a great addition to any developer's toolkit for smoother network management.

🆔 @hackernewsgithubprojects

📦 frangelbarrera/osint-bible

The Ultimate OSINT Resource Guide

This repository serves as a massive, curated collection of open-source intelligence resources designed to help researchers navigate the complex world of digital investigation. By centralizing essential tools, proven methodologies, and strict ethical standards, the project provides a structured framework for conducting responsible research. It addresses the common challenge of finding reliable information by organizing legal, publicly available assets into clear, actionable categories. Whether you are refining your investigative techniques or looking for specialized tools, this evolving guide offers a solid foundation for your work. Digging into these resources is a perfect way to sharpen your digital research skills.

🆔 @hackernewsgithubprojects

📦 run-llama/notebookllama

Build Your Own AI Podcast Tool With NotebookLlaMa

NotebookLlaMa provides a fully open-source framework to build a customized, AI-driven alternative to NotebookLM using LlamaCloud. This project enables users to transform documents into engaging, multi-speaker podcast conversations through a structured workflow. It combines powerful LLMs with ElevenLabs speech generation to turn transcripts into natural-sounding audio dialogues. The software includes tools for document management, interactive chat, data visualization, and observability dashboards to monitor the entire pipeline. Whether you are generating technical discussions or educational content, this repository offers a complete toolkit for managing and synthesizing your documents into an immersive, audio-based format.

🆔 @hackernewsgithubprojects

📦 meitarbe/cognetivy

Stop Losing Your AI Agent's Work with Cognetivy

Cognetivy is the open-source state layer that finally turns chaotic AI coding sessions into structured, traceable workflows. It solves the problem of important context vanishing into ephemeral chat logs by acting as a persistent memory and process manager for your agents. By utilizing a local studio with a visual interface and a robust execution engine, it allows you to define workflows, track individual runs, and organize reasoning artifacts into collections. It is a powerful tool for developers who need auditability and repeatability in their AI-assisted tasks, ensuring your AI intern keeps its work organized and verifiable.

🆔 @hackernewsgithubprojects

📦 yoheinakajima/activegraph

Build Long-Running, Auditable Agentic Systems with Active Graph

You see a complex system trace unfolding as an event-sourced log where every action is recorded and fully auditable. Active Graph provides a reactive framework for building long-running agentic systems by treating your data as a shared graph rather than isolated chat conversations. It allows behaviors to react to specific events and graph patterns, enabling more reliable and deterministic logic. You can branch any run into an independent fork to test new hypotheses, structurally diff the results against the original, and replay history without re-executing expensive tasks. This tool is built to bring transparency and control to complex agent workflows.

🆔 @hackernewsgithubprojects

📦 ksimback/looper

Design Better Agent Loops Before You Run Them

Looper is a design tool for Claude Code that prevents bad automation by requiring you to build and verify a loop structure before execution begins. Instead of letting an agent run unchecked, this skill interviews you to define clear goals, programmatic checks, and review gates, often involving a second model to provide an objective critique. It generates a portable specification, including a structured plan and termination guards, which can be run immediately in your session or later via an external runner. This approach helps ensure your agents have a clear definition of done and reliable error handling.

🆔 @hackernewsgithubprojects

📦 ahmaddarkhalil/hoi-detr

HOI-DETR: Detecting Hand-Object Interactions with AI

HOI-DETR is the transformer-based framework that accurately detects hands, held objects, and their complex interactions in a single forward pass. By building on the powerful Co-DETR architecture, it introduces a specialized interaction module capable of identifying both primary objects touched by a hand and secondary tools acted upon through those objects. This system significantly improves detection benchmarks, offering a robust solution for understanding intricate manual tasks. It even includes refined annotations to correct common dataset errors, making it a reliable tool for researchers looking to advance computer vision. Explore this repository to master advanced interaction detection for your projects.

🆔 @hackernewsgithubprojects

📦 ahmetvural79/camerarealtimestyle

Control Your Camera Styles With Hand Gestures

Your webcam feed instantly shifts into an artistic style like anime or claymation simply by pointing your index finger left or right. This project uses browser-based hand tracking with Google MediaPipe to recognize your gestures and trigger real-time transformations via the flux-2-klein model. By detecting whether you point or hold an open hand to reset, it provides a completely hands-free way to cycle through visual filters. It is a clever demonstration of integrating low-latency AI streaming with gesture control to create interactive video effects. Grab the code to customize your own creative webcam experience today.

🆔 @hackernewsgithubprojects

📦 mohitsoni48/turbollm

Run Local LLMs Fast with Zero Hassle

Optimize and run any local LLM engine directly on your hardware without the overhead of heavy software like Electron or Python. This tool provides a polished web interface and an API that is fully compatible with OpenAI and Anthropic, allowing you to run advanced tools like Claude Code on your own machine. It automatically benchmarks your GPU to apply the fastest settings, ensures your VRAM is utilized effectively, and supports community-built engine forks for maximum performance. Whether you are managing multiple models or sharing them across your network, this lightweight, offline-first application puts complete control over your local AI infrastructure.

🆔 @hackernewsgithubprojects

📦 jacob-bd/the-ai-counsel

Stop Trusting Just One AI: Build Your Own Deliberation Council

The AI Counsel replaces single-model responses with a multi-model system that uses structured deliberation and debate to deliver higher-quality answers. Instead of relying on one AI, this tool orchestrates several models to independently solve problems, peer-review each other, and synthesize a final, vetted conclusion. You can choose between a council mode for objective synthesis or an advisor mode where named personas, like a strategist or a skeptic, debate your questions in rounds to uncover risks and trade-offs. This project supports various cloud and local model providers, web search integration, and custom persona configurations for specialized decision-making, helping you arrive at better results.

🆔 @hackernewsgithubprojects

📦 dweep-desai/facegate-mac

Secure Your Mac Apps With Face Recognition

FaceGate acts as a native app-locker for macOS that lets you secure individual applications using face recognition, Touch ID, or a custom password. This utility intercepts app launches in real-time and requires authentication before granting access, effectively bridging a gap in native macOS security. The entire recognition pipeline runs locally on your device, leveraging the Apple Neural Engine to process face embeddings without any data leaving your machine. With features like liveness detection to prevent spoofing and per-app session timers, it offers a practical layer of privacy. Install it to add a modern authentication barrier to your sensitive applications.

🆔 @hackernewsgithubprojects

📦 imlixinyang/flashworld

Generate 3D Scenes in Seconds with FlashWorld

A detailed 3D environment materializes on screen almost instantly from a single text prompt or image input. FlashWorld is a powerful research project that enables high-quality 3D scene generation in mere seconds by leveraging advanced neural rendering techniques. This tool is designed to solve the challenge of slow scene creation by providing a fast, efficient workflow for developers and creators. It offers both a local web interface and a command line tool, allowing users to export results in versatile formats like PLY and SPZ. Explore this repository to accelerate your 3D generation tasks and streamline your creative pipeline today.

🆔 @hackernewsgithubprojects

📦 ffroliva/gflow-cli

Automate Google Flow Video Generation from Your Terminal

Control Google Flow directly from your terminal to generate high-quality AI images and videos without ever opening the web interface. This unofficial tool allows Ultra and Pro subscribers to batch process prompts efficiently, reuse characters consistently across different shots, and build automated content pipelines. By using a persistent Playwright session to handle authentication and reCAPTCHA, it streamlines your workflow while maintaining the full power of the underlying models. It is an excellent way to turn repetitive generation tasks into simple scripts. Install this command-line utility today to start integrating professional AI generation directly into your own automation stack.

🆔 @hackernewsgithubprojects

📦 cassie07/agentskill_survey

Understanding Agent Skill Evaluation and Evolution

Navigate the landscape of artificial intelligence agent development by exploring systematic frameworks for how agents create, use, and evolve their internal skills. This repository serves as a comprehensive survey that organizes modern research into clear paradigms like execution feedback, trajectory distillation, and reinforcement learning. By centralizing references for various skill-centric benchmarks and general-domain evaluation methods, it highlights structural gaps in current testing metrics to help researchers improve agent reliability and safety. Use this resource to better understand the lifecycle of agentic systems and identify key open challenges for your next project in this evolving field.

🆔 @hackernewsgithubprojects