📦 amathislab/terra

TERRA

Turn raw human movement videos into physical reality by guessing the hidden ground beneath them. Terra takes motion capture data and uses it to reconstruct the actual terrain, like stairs or ramps, that a person is walking on. Then it maps that movement onto a detailed muscle and skeleton model to train robots that can actually navigate real-world obstacles. It is a clever way to bridge the gap between simple video tracking and complex physical control. If you want to see how computers understand the physical world through movement, Terra is the tool that makes that happen. It is a fascinating look at the future of realistic robot locomotion.

🆔 @hackernewsgithubprojects

📦 groundingpi/groundingpi

One Model, Every Object: The Grounding PI

Grounding PI is a single four-billion parameter model that actually points to things in photos, not just describing them. It unifies finding objects, reading text, and locating buttons on screens into one smart system. Instead of needing a different tool for every job, this one model handles it all with state-of-the-art accuracy. It’s like giving a robot a universal vision brain that understands where everything is. If you want to build systems that truly see the world, this is the foundation you need to know about. It’s clever, efficient, and surprisingly capable for a model of its size. Keep that in mind the next time you build something visual.

🆔 @hackernewsgithubprojects

📦 tbee6061-ctrl/studio-live-window-capture

PixelGlass: The End of Magenta Screens

PixelGlass is the frame capture toolkit that finally refuses to accept the magenta lie. You know the struggle: you launch a Roblox Studio playtest, and instead of your beautiful game, you get a flat, unapologetic slab of bright pink. That is a renderer refusing to hand over the pixels. PixelGlass solves this by peeking under the hood at the operating system level to grab the real image, even if the engine is being stubborn. It then checks that image for other common glitches like pure black or white, and if something looks wrong, it automatically tries a backup method until it gets the truth.

🆔 @hackernewsgithubprojects

📦 jacobjandon/onionclaw

OnionClaw: AI Agents Go Dark

Hand an AI agent the keys to the dark web, and it does not just look around; it investigates. OnionClaw lets artificial intelligence search hidden services, scrape anonymous pages, and analyze the results using large language models. Instead of manually checking sites, you type a query, and the tool automates the entire process, from finding data to summarizing threats. This is fascinating because it removes the human speed limit from security research. While meant for defensive work, the code highlights how close we are to fully autonomous online operations.

🆔 @hackernewsgithubprojects

📦 psmux/deskvnc

DeskVNC: The Remote Client That Lets AI Drive Your Computer

DeskVNC allows an AI agent to drive remote desktops without installing any software on the target machine. Most remote clients just connect you to a screen, but this one adds a control layer where an assistant can see, click, and type directly over standard connections. It matters because it reaches locked-down systems that usually reject automated tools, and a human can instantly take back the wheel if something looks wrong. The app handles VNC, RDP, and SSH in one window, saving you from juggling different apps for every computer. If you want automation that respects your security rules, this is the one to watch.

🆔 @hackernewsgithubprojects

📦 axiomcodeai/axiomcodegraph

AxiomCode Graph: Stop Guessing, Start Knowing Your Code

Turn your entire codebase into a precise map for your AI tools. AxiomCode Graph uses formal logic to trace exactly how every function connects to others, removing the guesswork from code navigation. Instead of relying on basic text search that misses hidden links, it builds a knowledge graph that shows you the real connections between parts of your project. This means your AI agents can work with complete accuracy, saving time and ensuring they never miss a crucial piece of logic. It’s a smarter way to understand your code, making sure every change is grounded in fact rather than assumption.

🆔 @hackernewsgithubprojects

📦 savannahfeder/agentbox

Agentbox: The Inbox for Coding Agents

Agentbox turns a wall of chaotic terminal windows into a single, organized inbox where dozens of coding agents work quietly until they need your attention. Instead of staring at separate chats and waiting for each one to finish, you drop tasks into rows and walk away while the software runs on your existing subscription. The most surprising part is how the priority system works; you tag tasks as urgent, and the app automatically queues the most important work first, ensuring your critical projects never wait behind side tasks. When an agent finishes, it surfaces a brief summary so you can review the work instantly rather than digging through logs.

🆔 @hackernewsgithubprojects

📦 trailhq/trail-code

Trail-code: Why Your Coding Agent Needs a Memory

Trail-code gives coding agents like Claude Code a persistent memory of your codebase so they stop relearning from scratch every time. It builds a map of your entire project, tracking every function and dependency, so the agent instantly knows where things are and what might break if you change them. But the real kicker is the learnings. When you correct the agent on a decision, like why a retry limit is set to four, it saves that context as a simple file in your repo. Next time, that agent starts with the answer already in hand, skipping hours of blind searching.

🆔 @hackernewsgithubprojects

📦 harbor-framework/terminal-bench

Terminal-Bench: The Ultimate Test for AI Agents

Every major AI agent builder is using Terminal-Bench to track progress and compare capabilities because it measures the frontier of agent work with a diverse, difficult, and high-quality set of tasks that evolve over time. It is a continuous benchmark published on the Harbor Hub, allowing developers to test their agents and models against real-world challenges in a sandboxing environment. The project actively seeks contributors to add new, challenging tasks, ensuring the benchmark remains a rigorous standard for evaluating AI performance.

🆔 @hackernewsgithubprojects

📦 bit-datalab/edit-banana

Turn Any Screenshot Into an Editable Diagram

Stop redrawing diagrams from scratch. Edit Banana takes a flat image of a flowchart or technical schematic and turns it into a live, editable file where every box, line, and label is separate. It uses smart vision models to find the shapes and text, then rebuilds the whole thing in a professional diagramming tool. No more tracing over PDFs. If you have ever had to rebuild a diagram because someone sent you a screenshot, this tool fixes that exact problem. It saves hours of tedious redrawing by doing the heavy lifting for you.

🆔 @hackernewsgithubprojects

📦 limecloud/lime

Lime: The AI Agent That Actually Finishes

Lime is the open-source AI agent that actually finishes the work. It is not just a chat box; it is a full-stack partner that lives in your desktop app and terminal, ready to handle real engineering tasks. While other tools stop at suggestions, Lime dives into your files, runs your tests, and executes terminal commands to build, fix, or research what you need. It can even split complex jobs across multiple agents, keeping every step visible so you can review exactly what it did. You get a powerful assistant that respects your permissions while delivering inspectable results.

🆔 @hackernewsgithubprojects

📦 xykong/flux-markdown

FluxMarkdown: The Finder Preview That Does It All

FluxMarkdown is the QuickLook extension that finally makes your Finder previews look like a polished website. Instead of seeing raw text when you press space on a document, this tool instantly renders diagrams, complex math, and interactive charts right inside the preview window. It turns a simple file peek into a full reading experience, complete with a clickable table of contents and the ability to save your work as a PDF. If you live in Markdown files, this is the upgrade you have been waiting for to make browsing your notes actually pleasant.

🆔 @hackernewsgithubprojects

📦 nvlabs/aspire

ASPIRE

ASPIRE solves a Rubik's Cube with a real robot arm, and it does not use traditional neural network weights to learn how. Instead, this system treats the robot's skills like a library of code that an artificial intelligence agent can read, test, and improve over time. The agent acts like a curious developer, running physical experiments to figure out how to grip objects or move joints, then saving the successful movements as reusable skills. This approach lets the robot adapt to new tasks without needing to be retrained on massive datasets. It is a fascinating shift from heavy computation to practical, iterative problem solving.

📰 https://news.ycombinator.com/item?id=50123746

🆔 @hackernewsgithubprojects

📦 maxmiksa/autonomous-company

autonomous-company

Spin up a digital firm that actually builds things while you sleep. Autonomous Company runs a continuous loop on your own machine, spinning up fourteen distinct AI agents to handle the heavy lifting. Each agent adopts a specific expert mindset, like a CEO using Bezos logic or a CTO focusing on failure-proof architecture. They research, code, and critique their own work, all while you just watch a local dashboard update in real time. It is the closest thing to hiring a remote team that costs nothing but your electricity. You get a self-managing workforce that works around the clock without the usual corporate bloat.

🆔 @hackernewsgithubprojects

📦 jordyzomer/lemmalog

Lemmalog: The Memory Engine for AI Agents

Lemmalog is the deductive database that turns agent memory into a verifiable, logical model rather than a fuzzy collection of text snippets. It solves the problem of AI agents forgetting or misremembering by using a logic engine to track exactly where every fact came from and how it changes over time. Instead of just storing text, it builds a structured knowledge graph that can prove its own conclusions and update efficiently as new information arrives. This means your AI assistant stops guessing and starts reasoning with confidence, giving it a reliable brain that remembers the truth, not just the last thing it read.

🆔 @hackernewsgithubprojects

📦 samuelfaj/distill

Distill: The Token Saver for Coders

Distill is a lightweight terminal tool that cuts the cost of using AI coding assistants by up to eighty-seven percent while keeping the same level of quality. It works by distilling your code context, so the AI only sees the most relevant parts of your project instead of every single file. This means you can connect your existing Grok or Codex subscription and get far more work done for far less money. It is built in Rust for speed and runs right in your terminal, making it a practical upgrade for anyone tired of high token bills.

🆔 @hackernewsgithubprojects

📦 satypardus/wowdecomp

They Rewrote World of Warcraft

Take a twenty-year-old World of Warcraft client, strip away the compiled machine code, and rewrite it all in human-readable C++ so anyone can actually read the engine. This is exactly what wowdecomp does. It reconstructs nearly every single function from the original binary, tagging each one with its exact memory address so you can verify it matches the source. The result is a complete, playable game client where the internal logic is finally open for inspection. Instead of guessing how the code works, you can just look at it. It turns a closed black box into a transparent piece of software that developers can actually study and understand.

🆔 @hackernewsgithubprojects

📦 anujasid/mcp-for-blender-pro

MCP for Blender Pro: AI that builds your 3D scenes

MCP for Blender Pro lets an artificial intelligence directly manipulate your three-dimensional workspace inside Blender by looking at your scene and writing the necessary code for you. This tool solves the problem of manually scripting repetitive modeling tasks by letting you describe your goal in plain language while the assistant handles the technical construction. It is useful for artists who want to quickly prototype layouts without leaving their creative flow or writing complex scripts from scratch. You can even set up a team of agents where one plans the work, others build the objects, and a final reviewer checks the result before you approve the changes.

🆔 @hackernewsgithubprojects

📦 victorchen96/deepseek_v4_rolepaly_instruct

DeepSeek V4 Roleplay Instruct: How to Control AI Thoughts

Take direct control over how DeepSeek V4 thinks inside its roleplay mode. This repository gives you the exact prompt codes to paste into your first message to force the AI into one of two distinct modes. You can make it act like a method actor, complete with internal monologues and emotional reactions, or switch it to a cold, pure logic mode for structured analysis. It is a simple tweak that fixes the messy, inconsistent thinking you usually get out of the box. Just copy the provided text, hit send, and watch the AI's thought process change completely.

🆔 @hackernewsgithubprojects

📦 tgp482/black-xberecomp

Black: A 2006 Xbox Game Gets Modern PC Life

A 2006 Xbox shooter now runs natively on your PC with modern graphics, thanks to Black XBE Recomp. This project uses a special tool to recompile the original game code, meaning it is not an emulator running old hardware but a fresh, native program built for Windows. The standout feature is the ability to remove the old thirty frame per second cap, letting the game run at your monitor’s full speed with crisp high definition visuals. It also adds proper mouse and keyboard support, so you can play with precision instead of relying on a game controller.

🆔 @hackernewsgithubprojects