📦 transtractor/transtractor-lib

Transtractor-lib

Transtractor-lib turns messy PDF bank statements into clean data without using any artificial intelligence. Built in Rust for speed, it uses strict rules to find transactions based on their exact position on the page rather than guessing from text. You can plug this into Python for analysis or run it in your web browser. It handles weird date formats and different bank layouts by just following the layout structure. It is fast, predictable, and completely free to use. Grab the code if you need reliable financial data extraction that actually makes sense.

🆔 @hackernewsgithubprojects

📦 donchitos/claude-code-game-studios

Build Games with 49 AI Agents

Turn a single Claude Code session into a full game development studio. Instead of chatting with one general assistant that might write messy code, you get 49 specialized AI agents organized like a real studio. There are directors guarding the vision, department leads owning specific domains, and specialists doing the actual coding and design. It solves the problem of solo AI development by adding structure, quality checks, and a clear hierarchy. You still make every decision, but now you have a team that catches mistakes early and keeps everything organized from brainstorm to launch.

🆔 @hackernewsgithubprojects

📦 swaroop2004/proven-viral-content-system

Proven Viral Content System

Proven Viral Content System turns simple text prompts into ready-to-post videos for Instagram, TikTok, and YouTube without writing code. It is built for AI coding assistants like Cursor or Claude, using a chat-based workflow where you guide the process with simple commands. You start by setting up your brand, then the tool researches trending ideas and helps you brainstorm concepts tailored to your audience. The standout feature is its ability to generate actual MP4 video files by connecting to the Magic Hour API, handling everything from detailed prompt writing to downloading the final clip. You can even preview results without spending credits.

🆔 @hackernewsgithubprojects

📦 pradipta/wallfacer

Wallfacer: The AI Coding Session Manager

Wallfacer organizes the chaotic mess of AI coding sessions by creating a single searchable index of your work across Claude Code, Cursor, Kiro, and Codex. Instead of digging through scattered, unnamed transcript files on your hard drive, this tool reads them safely without touching the original data, then lets you name, tag, and group every conversation in a clean interface. You can instantly resume any past chat, rename old work, or search for specific prompts across all your agents in one place. It turns a week of scattered AI experiments into a structured, easy-to-find library of your actual progress.

📰 https://news.ycombinator.com/item?id=49192219

🆔 @hackernewsgithubprojects

📦 aymanbagabas/drift

Drift: A Git Diff Pager That Actually Wants to Be Looked At

Drift turns those boring command-line diffs into a vibrant, clickable terminal experience that makes code review actually enjoyable. Instead of scrolling through endless gray text, you get a full-screen interface with syntax highlighting, a resizable file sidebar, and word-level changes that pop with color. It even watches your repository in real-time, so you can see edits appear instantly while you work. It works as a drop-in replacement for your default git viewer, requiring zero setup to start using right away. Give your code reviews a visual upgrade today.

📰 https://news.ycombinator.com/item?id=49206227

🆔 @hackernewsgithubprojects

📦 shawnpana/phone-harness

Phone Harness

You can let an artificial intelligence control your real iPhone directly from your Mac. This project bypasses jailbreaking and complex automation tools by using Apple's built-in iPhone Mirroring feature. It works like a digital puppeteer where a computer program takes screenshots through the mirroring window, reads the text on your screen using built-in vision tools, and then sends simulated taps and swipes to the phone. Essentially, it gives an AI agent eyes to see the screen and hands to click buttons, letting it open apps or type messages for you without needing special developer permissions or third-party drivers.

🆔 @hackernewsgithubprojects

📦 alvinreal/awesome-openclaw-tips

awesome-openclaw-tips

awesome-openclaw-tips is the practical guide that turns chaotic OpenClaw setups into reliable, cost-efficient workflows. Most people struggle with memory leaks and expensive token bills, but this repository solves that by providing tested, copy-paste tips for memory management, automation, and multi-agent systems. Instead of vague advice, you get exact config changes and implementation prompts you can run immediately. The coolest part is the heartbeat checklist system, which helps you schedule regular checks for email, calendar, and tasks without wasting compute. It basically teaches you how to keep your AI assistant working hard only when it needs to.

🆔 @hackernewsgithubprojects

📦 datamllab/a2e

A2E Agent Auditing Engine

A2E is an open-source platform for auditing AI agents end to end. It lets you pair any benchmark dataset with any agent framework like LangChain or CrewAI and run experiments through a single command. The engine automatically captures every step, logging LLM calls and tool usage into detailed traces you can view in a local interface. Instead of just checking if the final answer is right, it scores the whole process, analyzing planning, efficiency, and tool selection. This gives developers full visibility into how their agents actually think, not just whether they passed the test.

🆔 @hackernewsgithubprojects

📦 tencent/yolo-master

YOLO-Master: Real-Time Object Detection

Tencent released a new research prototype called YOLO-Master that mixes two powerful ideas to make object detection faster. Instead of using one giant brain for every image, this system picks smaller, specialized experts only when they are needed. This dynamic approach saves computing power while keeping the speed high enough for real-time video. The code is based on official research presented at a major computer vision conference. It shows how splitting tasks between different neural network parts can improve performance without slowing things down. Developers can explore this open-source model to see how modern detection tools are evolving beyond standard single-model designs.

🆔 @hackernewsgithubprojects

📦 jtydhr88/comfyui-ultrashape1

ComfyUI UltraShape 1 Mesh Refinement

Take a rough 3D mesh and instantly sharpen it with ComfyUI UltraShape 1. This plugin adds image-guided refinement to your workflow, turning blurry or blocky geometry into high-quality, detailed models. You feed it a coarse mesh from another tool and a reference photo, and it uses deep learning to fill in the missing details and sharpen the edges. It works directly inside your existing ComfyUI setup, supporting common file formats and offering low-vram modes for smoother performance. This makes upgrading basic 3D assets to professional quality surprisingly simple and accessible for anyone building scenes or characters.

🆔 @hackernewsgithubprojects

📦 idollab/anytrack

AnyTrack: Tracking Objects with Any Data

Track moving objects in videos using any kind of data input you have. This project unifies visual object tracking by letting models adapt to different modalities like text, audio, or standard images. Instead of being locked into just seeing pixels, AnyTrack accepts various data types to identify and follow targets. It solves the problem of rigid tracking systems by offering flexibility across different sensory inputs. This makes it useful for complex scenes where visual cues alone might fail. The core idea is simple: give it any relevant data, and it finds the object. It is a fascinating step toward more adaptable computer vision tools that work with diverse information sources.

🆔 @hackernewsgithubprojects

📦 h-embodvis/simwam

SimWAM: Fast Self-Driving Planning

SimWAM lets you train an autonomous driving planner by borrowing smarts from video generation, then throws the video part away. It co-trains a heavy video model and a lightweight action model, using the video’s understanding of physics to teach the planner how traffic moves. Once the training is done, you discard the video branch entirely. This leaves a super-fast, self-contained system that predicts driving paths directly from camera images without any heavy lifting. The team even used reinforcement learning to fine-tune the driving style, achieving top-tier results on navigation benchmarks with incredibly low latency. It is a clever shortcut to building efficient self-driving software.

🆔 @hackernewsgithubprojects

📦 spikelab-jhu/trace-active-reconstruction

Trace Active Reconstruction

trace-active-reconstruction stops robots from wasting time looking at the same spot twice. Instead of looping over already known areas, this project uses a clever planner that actively avoids redundant views. It forces the camera to hunt for fresh, informative geometry until it has fully mapped the environment. The system builds a real-time map and adjusts its path on the fly to maximize what it sees. It is built for simulation but offers a clear window into how smart trajectory planning works. Watch a robot efficiently explore a room in just minutes, proving that smart planning beats random wandering every time.

🆔 @hackernewsgithubprojects

📦 danielmiessler/pai

Pai: Your Personal Growth Engine

Take control of your personal development with Pai, a tool that turns artificial intelligence into a dedicated growth coach. It works by constantly comparing where you are right now against where you actually want to be, then guiding you through a simple step-by-step process to close that gap. Instead of just giving generic advice, it helps you build a personalized system for life and work that adapts as you improve. You can use it to set clear goals, track your progress, and make smarter decisions every single day. It’s like having a wise mentor who knows your story inside and out, helping you climb higher without getting stuck.

🆔 @hackernewsgithubprojects

📦 maxfreedompollard/compartment

Encrypted Offline AI Memory

Compartment gives your AI agent a permanent, private memory that actually works. Most assistants forget everything the moment a chat ends, but this tool saves every decision, preference, and detail you share, keeping it safe on your own computer. It runs completely offline with zero cloud connection, encrypting every byte including the search indexes so nothing can be stolen or tracked. The surprise? It ships with six thousand pre-loaded facts about computers, codes, and physics, letting agents operate faster without needing the internet at all.

🆔 @hackernewsgithubprojects

📦 eternityspring/shuohao-skills

Turn Any Novel into a Character Bible

Shuohao Skills is the creative tool that turns a raw novel into a complete character design bible in seconds. You feed it a story and it scans the text to extract every character, merging different names into one profile and backing every detail with exact quotes from the book. The real magic is the auto-generated model sheet for each person, giving you a bust portrait, full body turnaround, and key detail close-ups all in one clean layout. You can even switch the visual style to look like a Studio Ghibli film or stay realistic.

🆔 @hackernewsgithubprojects

📦 mco-org/mco

MCO: Compare AI Coding Agents

Run multiple AI coding agents on one task, compare their raw answers side-by-side, and decide which to trust before acting. No guesswork. Just clear, parallel perspectives from tools like Claude, Codex, and Pi. Check it out. Run MCO to orchestrate AI coding agents. Give them the same task, watch them work in parallel, and then compare their actual raw answers side by side. It lets you pick specific tools like Claude or Codex, run them simultaneously, and keep their unedited responses for review. This avoids trusting a single blind spot by letting you see where agents agree or disagree before you commit to code.

🆔 @hackernewsgithubprojects

📦 jonexaiorg/jonex

Jonex: Turn Raw Data into Structured Knowledge

Jonex lets you turn messy documents, videos, and audio into organized, AI-ready knowledge you can actually use. Instead of just searching through files, it builds a smart knowledge graph that understands how different pieces of information connect. You upload your content, and the system parses every type of file to extract facts, then compiles them into a structured ontology. This means when you ask a question, the AI reasons through the connections first, giving you precise answers with clear sources. It is like giving your entire company library a brain, so you get accurate, traceable insights instead of generic summaries.

🆔 @hackernewsgithubprojects

📦 xiaobiaodu/mobile-gs

Mobile-GS: Real-time 3D on Your Phone

Mobile-GS lets you render detailed three-dimensional scenes directly on your mobile device, turning your phone into a powerful 3D viewer. Usually, this kind of heavy lifting requires expensive desktop computers, but this project shrinks that technology down so it actually works on handhelds. It achieves this by compressing the visual data and optimizing how the graphics card draws it, allowing for smooth, real-time exploration of complex environments without draining your battery or lagging. This is genuinely exciting because it brings professional-grade 3D visualization to devices we already carry every day, opening up new ways to view digital spaces anywhere you go.

🆔 @hackernewsgithubprojects

📦 nakasyou/local-mcp

local-mcp

local-mcp is a security-first tool that lets artificial intelligence agents edit your computer files without giving them unlimited access. It wraps sensitive operations in a strict sandbox that blocks network access and limits what the agent can do, forcing it to ask for your permission before touching anything important. You keep total control by approving each action through a simple terminal interface, creating a safe bridge between your local projects and automated coding assistants. It turns risky blind automation into a transparent, auditable process you can trust.

🆔 @hackernewsgithubprojects

📦 oil-oil/codex-deepseek-subagent

Codex DeepSeek Subagent

The Codex DeepSeek Subagent lets you plug DeepSeek directly into OpenAI’s Codex desktop app as a native helper without touching your main model settings. You install a simple skill, hand over your API key once, and the tool verifies the connection by routing a test task and checking the response for a specific confirmation code. It saves your key securely in your operating system’s credential manager and backs up your existing config so you never lose anything. After that, you just ask Codex to use the DeepSeek helper for text tasks while your main agent handles the heavy lifting.

🆔 @hackernewsgithubprojects