📦 rikyz90/shibaclaw

Run a Private, Secure AI Agent on Your Own Machine

Manage your own private AI assistant with a self-hosted, security-focused agent that keeps your data local and secure. This platform provides a native web interface and desktop application, allowing you to connect to over twenty different AI providers while maintaining strict privacy. It features a sophisticated three-level memory system for long-term operational continuity, alongside built-in automation, task scheduling, and support for the Model Context Protocol. With robust defenses like install-time package auditing and prompt-injection wrapping, you can automate complex tasks reliably. Take full control of your digital workspace today with this versatile and deeply integrated AI agent.

🆔 @hackernewsgithubprojects

📦 headroomlabs-ai/headroom

Slash Your LLM Token Costs with Headroom

Headroom is an open-source tool designed to reduce token consumption by sixty to ninety-five percent for your large language model workflows. By compressing tool outputs, system logs, file data, and retrieved information before they reach the model, it maintains the same quality of answers while significantly lowering operational costs. This project functions as a library, a proxy, and an Model Context Protocol server to integrate seamlessly into existing pipelines. It helps developers manage context windows more efficiently and save money on expensive API calls. Whether you are scaling RAG applications or managing complex logs, this tool provides essential optimization.

📰 https://news.ycombinator.com/item?id=48627072

🆔 @hackernewsgithubprojects

📦 simplifaisoul/osiris

OSIRIS: The Open Source Global Intelligence Dashboard

Osiris functions as a production-grade intelligence platform that aggregates global real-time data into a single GPU-accelerated interface. Built using Next.js and MapLibre, it visualizes diverse information layers including live flight tracking, maritime activity, earthquake monitoring, and public CCTV feeds. The platform features a specialized reconnaissance toolkit capable of port scanning, DNS resolution, and cryptocurrency wallet tracing, which automatically cross-references data against international sanctions lists. By processing vast amounts of geographic and cyber-threat data with high-performance WebGL rendering, this open-source tool provides users with comprehensive situational awareness. Explore global events through this technical dashboard to monitor and analyze complex intelligence feeds.

🆔 @hackernewsgithubprojects

📦 raiyanyahya/recall

Give Claude Code Permanent Memory Offline

Recall provides Claude Code with durable, fully-local memory by automatically logging your sessions and condensing them into a concise summary. It solves the cold-start problem by tracking your project progress, goals, and open threads without needing external API calls or extra tokens. Using a built-in Python summarizer based on TF-IDF and TextRank, it creates a compact context file on your machine that you can load into new sessions. This keeps your workflow efficient and private while saving your subscription credits. Simply install the plugin to stop re-explaining your project and let your code history work for you.

📰 https://news.ycombinator.com/item?id=48622590

🆔 @hackernewsgithubprojects

📦 corsairdev/corsair

Build Powerful AI Agents with a Unified Integration Layer

Connect your AI agents to a wide range of external tools and services through a single, streamlined integration layer. This project simplifies the complexity of managing multiple connections by providing pre-built adapters for popular platforms like Slack, GitHub, Gmail, and Notion. It handles essential tasks such as authentication, webhook management, and database interactions, allowing developers to focus on building agent capabilities rather than maintaining fragile API integrations. Whether you are automating workflows or creating intelligent assistants, this infrastructure ensures your agents communicate reliably across your entire tech stack. Experience a cleaner, more efficient way to manage your integrations.

🆔 @hackernewsgithubprojects

📦 guohuiyuan/go-music-dl

Go Music DL: The Ultimate Multi-Platform Music Tool

Go Music DL is a powerful tool built in Go that aggregates music search and download capabilities across more than ten major platforms including QQ, NetEase, and Bilibili. This versatile project functions as a CLI tool, a desktop application, and a local web server, allowing users to search, stream, and batch download music with ease. It supports high-fidelity audio parsing, lyrics, and even manages local music libraries with metadata tagging. Whether you prefer a terminal interface or a graphical dashboard, this tool streamlines music collection and management into one unified, efficient experience for any platform.

🆔 @hackernewsgithubprojects

📦 slothflowlabs/duckle

Build Data Pipelines Instantly with Duckle

Design and run data pipelines locally by dragging and dropping nodes onto a visual canvas. This desktop application compiles your visual workflows directly into SQL, executing them at high speed through the DuckDB engine. You can effortlessly integrate hundreds of sources and sinks, from SQL databases and lakehouses to streaming brokers and SaaS APIs, without needing any servers or cloud infrastructure. It even includes a local AI assistant that helps you build pipelines by simply describing what you need in plain English. Your workspaces stay as simple, git-friendly files on your own machine, putting you back in control.

📰 https://news.ycombinator.com/item?id=48628614

🆔 @hackernewsgithubprojects

📦 layr-labs/d-inference

Darkbloom: Turn Your Idle Mac into a Private AI Cloud

Darkbloom transforms idle Apple Silicon Macs into a secure, decentralized network for running artificial intelligence models. It enables users to tap into high-performance compute power while ensuring privacy through end-to-end encryption and strict hardware attestation. The system uses a Go-based coordinator and a hardened Swift CLI to process requests directly on the Mac GPU via MLX, keeping data encrypted even from the machine owner. It supports standard OpenAI and Anthropic API formats, allowing developers to integrate it easily. Whether you want to monetize your idle hardware or build a private inference pipeline, this project demonstrates a highly secure model.

🆔 @hackernewsgithubprojects

📦 akmessi/vex

AI Video Editing Straight From Your Terminal

Edit videos using plain English commands directly in your terminal with this powerful AI agent. By simply describing the changes you want, the software handles complex tasks like trimming footage, removing silent gaps, or color grading your clips using intelligent automation. It safely edits a working copy of your video while maintaining a full project history, allowing you to undo or rebuild edits anytime. You can even generate custom B-roll and visual animations to match your narration automatically. Streamline your entire creative workflow by letting this terminal-native tool manage the technical heavy lifting for you.

🆔 @hackernewsgithubprojects

📦 paytonjjones/bsharp

BSharp: A Digital Tool for Teaching Absolute Pitch

Young children possess a unique neurological window for acquiring absolute pitch that closes around age six. BSharp is an open-source tool built to help children leverage this window through the Eguchi chord identification method. The software functions by playing specific piano chords that children must identify by associated colors. It features an adaptive weighting algorithm to prioritize harder chords and includes progress tracking for multiple users. By practicing briefly throughout the day, children learn to recognize these musical intervals reliably. This project provides a practical, offline-capable digital implementation for families interested in early childhood auditory development.

📰 https://news.ycombinator.com/item?id=48618488

🆔 @hackernewsgithubprojects

📦 spiritbuun/buun-llama-cpp

Boost Your LLM Context: Turboquant Explained

This specialized fork of llama.cpp increases available model context by two to three times without requiring additional video memory. By implementing Trellis-Coded Quantization, the software efficiently compresses the key-value cache while maintaining performance levels that often exceed standard uncompressed formats. It achieves this by using a five hundred twelve state trellis to optimize codeword assignments, enabling high-quality inference at very low bit rates. This project is particularly useful for users running large models on limited hardware, offering a practical way to fit significantly longer text windows into existing GPU setups. Explore this implementation to optimize your local model capacity.

🆔 @hackernewsgithubprojects

📦 routatic/proxy

Route Claude Code to Any Provider with Routatic Proxy

Connect Claude Code to powerful alternative AI providers like OpenCode Go, OpenCode Zen, or AWS Bedrock using this flexible Go-based CLI proxy. It sits between your development environment and these services, automatically transforming Anthropic API requests into native formats for your chosen models. The tool handles intelligent model routing based on your specific task—such as choosing models for long context, complex reasoning, or background operations—and includes features like automatic fallback chains, real-time streaming, and circuit breakers. This setup lets you leverage cost-effective or infrastructure-specific models without changing your existing workflow, ensuring a seamless and highly customizable coding experience.

📰 https://news.ycombinator.com/item?id=48629769

🆔 @hackernewsgithubprojects

📦 firecrawl/open-agent-builder

Build AI Agent Workflows Visually with Drag-and-Drop

Design and execute complex AI agent pipelines using a visual drag-and-drop interface. This project simplifies building multi-step automation by connecting agents, tools, and data transformation nodes directly on a canvas. Powered by Firecrawl, it handles web scraping and data extraction while providing real-time streaming updates during execution. You can incorporate human-in-the-loop approvals, conditional logic, and even custom tools through an extensible registry. Whether you are automating research or building sophisticated data pipelines, this tool offers a flexible way to manage and deploy your AI agents. Explore new possibilities for your next intelligent workflow today.

🆔 @hackernewsgithubprojects

📦 spotiflacapp/spotiflac-mobile

Manage Your Music Library with SpotiFLAC Mobile

Manage your personal music library with a powerful mobile utility built using Flutter and Go. This open-source tool enables high-quality audio management, allowing you to browse, search, and download tracks seamlessly. By leveraging a decentralized extension system, you can easily add new music sources without needing constant app updates. The interface is designed for simplicity, providing an ad-free and subscription-free experience. Whether you need to edit track metadata, handle album downloads, or organize your local files, this project keeps your music library under your complete control. Explore the possibilities of a truly custom, community-driven mobile music experience today.

🆔 @hackernewsgithubprojects

📦 bobbyiliev/101-linux-commands

Master Linux with 101 Essential Commands

This repository provides a comprehensive open-source eBook and command-line tool featuring 101 essential Linux commands that every developer or system administrator should master. It serves as a practical guide for navigating the terminal, managing file systems, handling disk operations, and organizing user permissions efficiently. By breaking down complex tools into categorized chapters and clear examples, the project helps users build foundational skills for daily operations. Whether you are automating tasks or troubleshooting a server, this resource streamlines the learning process for anyone working in a terminal environment. Explore the full collection to sharpen your command-line expertise today.

🆔 @hackernewsgithubprojects

📦 kinghacker0/whatsapp-osint

Mastering WhatsApp OSINT: A Powerful Investigative Tool

Gather intelligence on WhatsApp accounts by leveraging a specialized Python tool designed for cybersecurity professionals and researchers. This project integrates with the RapidAPI WhatsApp OSINT API to provide deep insights into contact profiles. You can easily retrieve profile pictures, verify business accounts, and analyze linked devices or privacy settings through an interactive terminal interface. It streamlines data collection for authorized security audits by automating queries across six specific endpoints. By requiring a valid API key, it ensures structured data retrieval while maintaining strict ethical boundaries for educational and investigative use, making complex profile analysis significantly more efficient.

🆔 @hackernewsgithubprojects

📦 nutlope/make-comics

Build AI Comic Books in Seconds

Advanced AI models can now generate full comic books by leveraging Google Flash Image 2.5 for visual panels and Qwen3 80B for narrative storytelling. This platform enables users to create consistent comic sequences by referencing previous pages and specific uploaded character images to maintain visual continuity throughout the story. Built with a modern stack including Next.js and Drizzle ORM, it provides a comprehensive interface for crafting stories and managing image storage via AWS. The project offers a practical framework for automated comic production that ensures characters remain recognizable across every panel. Try it to see how easily narrative art comes together.

🆔 @hackernewsgithubprojects

📦 mehmetyukselsekeroglu/eye_of_web

Eye of Web: The Open-Source OSINT Face Search Engine

Eye of Web functions as a sophisticated open-source OSINT platform designed for large-scale face recognition and identity analysis. It automates data collection across multiple web sources by employing specialized crawlers for Google, Facebook, Twitter, and Telegram. The system utilizes advanced algorithms like InsightFace for face detection and Milvus for high-performance similarity searching to cluster individuals and isolate specific targets from look-alikes. By integrating Selenium and Playwright, the tool mimics human browsing behaviors to efficiently gather data. This project offers a comprehensive framework for digital investigative research, allowing users to map connections and analyze relationships through a centralized web interface.

🆔 @hackernewsgithubprojects

📦 voltagent/awesome-codex-subagents

166+ Specialized AI Subagents for Your Codex Workflow

This collection provides over 166 specialized subagents designed to handle specific development tasks within the Codex environment. By using standardized TOML configuration files, these agents can be deployed globally or scoped to individual projects to automate everything from backend architecture and security audits to documentation and cloud infrastructure management. Each agent includes specific instructions and sandbox constraints to ensure safe, role-based interaction with your codebase. This library offers a structured way to delegate technical challenges to targeted AI assistants, allowing developers to optimize their workflows and maintain consistency across complex engineering projects through precise model routing and governance.

🆔 @hackernewsgithubprojects

📦 ai-builder-club/loop-engineer-template

Build Compounding AI Agent Loops

Loop engineer template provides a structured codebase harness for building autonomous agents that operate in compounding loops rather than simple task-by-task prompts. By utilizing a shared file-based memory and predefined skills, these agents can investigate issues, perform work, and log findings independently to ensure continuous progress. The framework centers on domain-based loops that integrate signals and durable documentation to manage complex workflows efficiently. This template allows developers to scaffold new agents, automate code verification, and maintain a historical record of actions, effectively transforming manual coding tasks into a self-driving system that compounds productivity over time.

🆔 @hackernewsgithubprojects

📦 apple/ml-lgtm

Scale Gaussian Splatting to 4K with LGTM

Generate high-resolution 4K imagery using feed-forward Gaussian splatting through this research implementation. While traditional methods often struggle to maintain performance at such high resolutions, this project introduces a native approach that predicts compact textured Gaussians to handle 4K output efficiently. The repository provides the complete framework to train, evaluate, and perform inference, including specialized support for textured 2DGS rasterization. By utilizing this pipeline, you can bridge the gap between fast feed-forward reconstruction and detailed, high-fidelity rendering for complex scenes. Explore the provided scripts to start processing your own high-resolution 3D data today.

🆔 @hackernewsgithubprojects