📦 clarkarch/tfm-tui

Tfm TUI: The Mouse-First Terminal File Manager

Clicking a file icon in your terminal just works. Tfm TUI is a Linux file manager that runs inside your terminal but feels like a desktop app, letting you drag, drop, and select files with a mouse instead of typing commands. It solves the friction of terminal navigation by adding real image thumbnails, a sidebar with your bookmarks, and an integrated terminal pane so you never lose your place. You can even drag files out of the terminal window and into other applications.

🆔 @hackernewsgithubprojects

📦 jub0t/wolfcut

WolfCut: The Free CapCut Alternative

WolfCut is a native desktop video editor built to be the free, open-source alternative to CapCut, meaning no watermarks, no subscriptions, and no account required. It runs a powerful Rust engine locally on your machine, handling everything from multi-track timelines to free automatic captions and voice filters without uploading your data to the cloud. The most impressive part is that it bundles its own tools, like FFmpeg, so you can install it and start cutting immediately on Windows, Mac, or Linux. This gives you full control over your creative work with a lightweight, private, and completely ad-free experience.

🆔 @hackernewsgithubprojects

📦 bitwisecook/tcl-lsp

tcl-lsp: The Ultimate Coding Assistant

tcl-lsp is the intelligent coding assistant that brings full modern support to the often overlooked Tcl language. While many developers write in this language for networking hardware or legacy systems, they usually lack real-time feedback and smart suggestions. This project solves that problem by acting as a bridge between your code editor and a deep understanding of Tcl and its specialized dialects, like those used in network devices. It provides instant error checking, precise autocompletion, and even helps with complex tasks like refactoring or security reviews. By connecting directly to your favorite editor, it turns a raw text file into a dynamic, responsive workspace.

📰 https://news.ycombinator.com/item?id=49481808

🆔 @hackernewsgithubprojects

📦 thurbeen/thurbox

Thurbox: The Terminal Manager for AI Coding Agents

Thurbox is the terminal interface that finally puts your AI coding agents on a leash. It lets you run multiple coding tools like Claude or Codex side by side, each isolated in its own Git branch. The killer feature is that the entire user interface is built from text files you can edit live. You can literally rewrite your app's layout without touching code or restarting the program. It’s like giving your AI a control panel to manage its own fleet of coding tasks while you just watch. If you want to orchestrate your AI workers without drowning in terminal commands, this is the tool you need.

🆔 @hackernewsgithubprojects

📦 tencent-hunyuan/hy4-preview

Tencent's 770B AI Model

Tencent has open-sourced a massive AI model with seven hundred seventy billion parameters, and it handles one million tokens of context. The Hy4 preview is built for real work, turning complex engineering and analysis tasks into shareable documents, spreadsheets, and playable game prototypes from a single prompt. It uses a mixture-of-experts design that activates only a fraction of its brain to keep it fast. Developers can deploy it easily using standard tools and fine-tune it for their specific needs. This early release is already competitive with top private models, making it a powerful new tool for builders.

📰 https://news.ycombinator.com/item?id=49483991

🆔 @hackernewsgithubprojects

📦 2018cx/gadc

GADC: The AI Trick to Shrink Massive Image Datasets

GADC is the PyTorch implementation of a method that drastically reduces the number of images needed to train high-quality AI art generators. This project tackles the massive cost of training diffusion models by selecting a tiny, geometrically smart subset of the original ImageNet data. Instead of forcing the model to memorize millions of photos, this approach condenses the dataset down to a manageable size while keeping the essential visual patterns. The result is a training pipeline that runs much faster and uses significantly fewer resources, yet still generates realistic images that rival those made from the full dataset.

🆔 @hackernewsgithubprojects

📦 mahimailabs/voicegateway

VoiceGateway: The Missing Dashboard for Your AI Voice Agents

Your voice agents are flying blind, and VoiceGateway fixes that. While most AI voice projects struggle with hidden costs and unpredictable lag, this tool acts as a single source of truth. It sits between your app and providers like OpenAI or LiveKit to track every second of latency and every dollar spent in real time. You get a visual map of exactly where your AI is stalling or breaking the bank, turning invisible backend chaos into clear, actionable data. If you are building voice agents, this is the control panel you actually need to keep them healthy and your costs predictable. Check out the code to see how it works.

🆔 @hackernewsgithubprojects

📦 calmrocks/ai-engineer-notebooks

Build Real AI Systems for Free

Build working AI systems from raw code using the AI Engineer Notebooks, a free collection of Colab projects that skips the heavy frameworks to teach you the actual mechanics of modern AI. This repository is a hands-on curriculum that runs entirely on a fast, no-cost API, letting you construct everything from basic prompts to complex agents and retrieval systems without spending a dime. The real magic is in the final section, where you don't just read about production issues, but actually debug a live support assistant as it fails in the real world. It’s the perfect way to prove you can ship real software, not just demo code.

📰 https://news.ycombinator.com/item?id=49471714

🆔 @hackernewsgithubprojects

📦 real-stanford/gated-memory-policy

Gated Memory Policy: Robots That Remember

A robot arm can now watch a human work and then execute the task in its own kitchen without a single line of code retraining. This Stanford project, Gated Memory Policy, teaches machines to store what they see in a flexible internal memory, allowing them to adapt to new situations on the fly. Instead of treating every movement as a blank slate, the system remembers past actions and adjusts its behavior based on context, much like a person recalling a previous experience to guide their next move. This is crucial for real world tasks where conditions change constantly, such as handling objects of varying sizes or navigating cluttered spaces.

🆔 @hackernewsgithubprojects

📦 jprx/darwin-vm

Boot an iPhone Kernel on Your Computer

Boot a real iPhone or Mac right on your desktop. Darwin VM takes Apple's operating system and runs it inside a standard emulator, skipping the screen and apps entirely. In seconds, you land in a root shell with full control to debug the kernel and compile your own programs. This is huge because it opens up Apple's usually locked down architecture for deep research, letting you see exactly how their latest chips run the OS. If you have ever wanted to peek under the hood of an iPhone, this is your ticket. Give it a try.

🆔 @hackernewsgithubprojects

📦 raullenchai/twinspark

twinspark: The Self-Healing AI Cluster

Twinspark takes two modest desktop computers and turns them into a single, resilient engine capable of running massive language models locally. The project solves a critical pain point for local AI developers: the fragility of multi-node setups. By using a self-healing cluster architecture, the system automatically recovers from crashes or power outages without manual intervention, ensuring your AI assistant is always ready to work. It also fine-tunes the decoding process to squeeze out high performance from limited hardware, allowing you to handle complex coding tasks with speed and reliability.

🆔 @hackernewsgithubprojects

📦 zju-real/ttpo

TTPO: Making AI Math Better Without Human Labels

Boosting a language model's math skills without a single human-written answer is possible thanks to TTPO. This project lets AI improve its reasoning directly on test problems by learning from its own attempts. It solves a major issue where standard voting methods fail because most guesses are wrong. TTPO spots that disagreement is a useful signal. It rewards consistent answers and penalizes confident errors. This creates a self-improving cycle that works even without perfect data. The result is a model that gets significantly better at difficult math just by practicing on its own. No labels needed, just smart self-correction. That is a powerful way to build smarter AI.

🆔 @hackernewsgithubprojects

📦 zhangzaibin/future-robots

Future Robots: The Multi-Arm AI That Teaches Bots to Work Together

Future Robots is the robotics research code that finally makes multiple robot arms work as a coordinated team. It solves the problem of rigid, single-task training by allowing agents to decompose goals into small, reusable skills and compose them on the fly. Instead of treating every task as a unique, memorized routine, the system learns atomic actions that can be rearranged to handle new problems. This approach lets a group of robots collaborate on complex, multi-step tasks they were never explicitly trained to perform together.

🆔 @hackernewsgithubprojects

📦 ryanssenn/gemma4.c

The 700 Line LLM

One single C file runs a full language model on your CPU, outpacing standard optimized engines by more than double in speed. gemma4.c is an educational project that builds the entire Gemma 4 inference pipeline in just seven hundred lines of pure C, with zero external libraries. It strips away the heavy frameworks usually required, leaving only the raw math of tokenization, matrix multiplication, and attention. The goal is not to replace professional tools, but to make the internal mechanics of large language models completely transparent. By seeing every line of code that turns text into predictions, developers finally understand exactly how the magic happens under the hood.

📰 https://news.ycombinator.com/item?id=49468286

🆔 @hackernewsgithubprojects

📦 lilmgenius/paperthin

Paperthin: The Agent Skill That Deletes

Paperthin fixes the biggest problem with AI coding assistants: they never delete. Instead of just piling on more code and comments, these skills force your agent to clean up. One key skill rewrites a messy draft from scratch, stripping away the clutter to leave only what actually works. It turns old engineering wisdom into automatic habits that keep your projects lean and readable. It is like having a strict editor who refuses to add noise, ensuring your code stays clean instead of rotting into a mess. If you are tired of AI bloat, this is the tool that makes subtraction your default.

🆔 @hackernewsgithubprojects

📦 jalen-brunson/comfyui-minimax-h3-pdd-acc

Generate Video and Audio in Just Eight Steps

ComfyUI MiniMax H3 PDD Acc lets you generate synchronized video and audio in only eight computational steps, skipping the usual forty-plus iterations that slow down creation. It works by fusing a specialized acceleration layer directly into the model, allowing the system to predict large chunks of the final output at once rather than building it pixel by pixel. This setup removes the need for guidance scaling, making the process significantly faster while maintaining high quality. The tool handles both video and sound together, ensuring they stay perfectly in sync without extra post-processing.

🆔 @hackernewsgithubprojects

📦 seeray11/openflow

OpenFlow Visual AI Builder

OpenFlow is the visual canvas that lets you wire multiple AI agents together like a assembly line. Instead of writing complex code to manage different artificial intelligence tasks, you simply drag role cards onto a screen and connect them. The real magic happens when these agents run in parallel. A planner can think while an architect designs and a coder builds, all working on your actual files at the same time. It turns abstract AI concepts into a simple, visual workflow you can see and control. You get the power of teamwork without the headache of manual orchestration.

🆔 @hackernewsgithubprojects

📦 elliottdehn/open-jobs

Find Jobs with AI: open-jobs

Turn your dream job description into a living search engine with open jobs, a free tool that helps you hunt for roles without spending a dime. Instead of sifting through thousands of results, you simply describe the role you want to a coding agent, which then embeds that description to find the most similar live job postings from millions of listings. It builds a local, interactive page on your computer where you can rate jobs as you browse, training the system to refine its matches in real time.

🆔 @hackernewsgithubprojects

📦 agent4science-utokyo/task-coevolve

Task-CoEvolve: The 80% Faster AI Optimizer

Cut your AI testing costs by eighty percent without losing accuracy, all thanks to Task-CoEvolve. This University of Tokyo project solves the expensive problem of constantly re-evaluating every single task when improving an AI agent. Instead of grinding through the entire list, it smartly picks only the tricky problems where different AI versions actually disagree. By focusing solely on these useful moments, the system learns faster and stays accurate. It is a clever, efficient way to make your AI better while spending far less computing power.

🆔 @hackernewsgithubprojects

📦 whispem/asm.fm

asm.fm: Making Music with Pure Assembly

Make a song without a single audio library. That is exactly what asm.fm does. It turns raw CPU math into actual sound by calculating every note by hand and writing the numbers straight to a standard wave file. The project proves you can build a full synthesizer, complete with filters and effects, using only basic system calls. It strips away the complex software layers to show exactly how a speaker moves when fed with simple numbers. If you have ever wondered how computers create music from scratch, this project offers a fascinating look at the mechanics underneath.

🆔 @hackernewsgithubprojects