📦 mibayy/token-savior

Token Savior: The AI Efficiency Trick

Token Savior is an MCP server that helps AI coding agents work significantly faster and more accurately without using up your expensive token budget. Instead of making the AI read entire files just to find one specific function, it builds a smart map of your codebase so the model can navigate by pointer rather than guessing. It also remembers key decisions and conventions from previous sessions, so it doesn't forget context when a chat restarts. In one benchmark, this tool helped an AI model score nearly 98 percent on a coding test while using eighty percent fewer tokens and finishing tasks in a fraction of the time.

🆔 @hackernewsgithubprojects

📦 ooples/token-optimizer-mcp

Token Optimizer MCP: Cutting AI Costs by 90%

Token Optimizer MCP cuts your AI coding agent costs by up to ninety percent. It works by intercepting the massive amounts of text and code that these agents send to large language models. Instead of paying to process the same files repeatedly, it uses smart caching and compression to remove the fat. Think of it as a personal manager that only hands the AI exactly what it needs, not the entire library. This is especially useful if you use multiple different AI tools, as it creates a shared knowledge graph across sixteen clients. Your agents learn from each other's mistakes and optimizations, so you stop paying for redundant work.

🆔 @hackernewsgithubprojects

📦 n1tr00-10/tiktok-signature

TikTok Signature Generator

Generate the hidden security codes that TikTok uses to verify every web request. This open source project recreates the exact algorithm TikTok uses to create what they call X-Gnarly, X-Bogus, and X-Dynosaur signatures. These are essentially digital fingerprints attached to your data. Without them, the TikTok website won't even talk to its servers. The project is a pure Python tool that mimics the encryption TikTok uses. It uses specific encryption methods like ChaCha20 and RC4 to build these codes exactly the way the official system does. It is interesting because it shows the engineering behind a system we normally just see working in the background.

📰 https://news.ycombinator.com/item?id=49258849

🆔 @hackernewsgithubprojects

📦 tonyd2wild/deepseek-v4-flash-vision-exp-dspark-1m-nvfp4-kv-2x-dgx-spark

DeepSeek V4 Flash Vision: 1M Context on Two Sparks

DeepSeek V4 Flash Vision is the two-node recipe that finally brings one-million-token image understanding to a modest DGX Spark pair. The single most surprising thing it does is keep the model fast and accurate while reading entire books or massive codebases, all while accepting direct image input, without melting your hardware budget. It works by squeezing the memory footprint of its context cache using a special low-precision format that fits a million tokens into just under twenty gigabytes of shared GPU memory. The recipe handles the tricky wiring of two machines acting as one giant brain, fixing silent bugs that usually cause half your speed to vanish without a warning.

🆔 @hackernewsgithubprojects

📦 bytechemistterminal/serum-vst-suite

serum-vst-suite: A Compact Audio Workstation

Build a full studio on your Windows laptop with Serum VST Suite, a lightweight digital audio workstation that packs professional recording, sequencing, and mixing tools into a single, simple app. It handles everything from MIDI piano rolls to basic noise reduction, so you can track, edit, and polish your music without juggling multiple heavy programs. The best part? It runs entirely offline with no extra dependencies, just download, unzip, and hit play. Whether you are mixing a quick beat or cleaning up a voice track, it keeps your creative flow moving without the usual software bloat.

🆔 @hackernewsgithubprojects

📦 apparitionseaman/mp3-downloader-studio

Mp3 Downloader Studio: The Audio Tool You Need

Create full tracks in a studio that actually feels like a real studio. Mp3 Downloader Studio is a lightweight audio environment built for speed, letting you record, beat-make, and mix without the bloat of professional software. It handles everything from low-latency recording to advanced mixing, so you can capture ideas before they fade. The setup is surprisingly simple; just unzip the file and run it. You get pro-level tools like real-time effects and plugin support, but the interface stays out of your way. It is perfect for creators who want serious sound design without the headache of heavy installations.

🆔 @hackernewsgithubprojects

📦 lukasniessen/archunitpython

ArchUnitPython: Stop Architecture Drift

ArchUnitPython is the architecture testing library that finally lets your codebase enforce its own structure. Instead of relying on code reviews to catch when your database layer accidentally starts importing from your presentation layer, this tool turns your architectural rules into automated tests. It maps out your entire dependency graph to spot circular imports and verify that your modules respect their boundaries. If someone breaks your clean architecture, the build fails immediately. It is the guardrail that keeps large Python projects from turning into spaghetti, ensuring your code stays organized without you having to manually audit every single import.

📰 https://news.ycombinator.com/item?id=49510523

🆔 @hackernewsgithubprojects

📦 xai-org/plugin-marketplace

What is the Plugin Marketplace for Grok?

Discover how to extend Grok Build with the official plugin marketplace from xAI. This repository acts as a curated index that connects your coding assistant to new capabilities like database skills and automation tools. Instead of downloading files directly, it points to trusted sources pinned to specific commits, which prevents silent updates and security risks. You can easily browse, install, and manage these add-ons to make your development workflow smarter. By locking in exact versions, it ensures your tools remain reliable and safe. It is the perfect way to supercharge your coding agent with precision and peace of mind.

🆔 @hackernewsgithubprojects

📦 hardenrun/aif

A Firewall That Stops AI Hacks Before They Happen

Your coding AI can accidentally leak your secrets, so this tool puts a hard stop on its fingers. AIF is a local firewall that intercepts actions from agents like Claude Code and Cursor before they run, blocking any command that looks like it is trying to steal data or break your machine. It runs entirely on your computer, so your code never leaves your desk. The best part is that it shows you exactly what it blocked, so you are not left guessing why the bot froze. It is like a bouncer for your artificial intelligence, keeping the party safe without slowing down the good times.

🆔 @hackernewsgithubprojects

📦 kosuke55/drawtonomy

Drawtonomy: The Browser Whiteboard for Driving Sims

Drawtonomy lets you sketch complex driving scenes and instantly watch them play out right in your browser, without installing a thing. It solves the headache of testing self-driving logic by turning a simple drawing tool into a full simulation engine. You draw lanes and cars, hit play, and the built-in engine runs the scenario to tell you if your test passed or failed. The coolest part is that everything happens locally, so your data stays private and the process is shockingly fast. It is the perfect bridge between a rough idea and a real, testable driving scenario.

📰 https://news.ycombinator.com/item?id=49257744

🆔 @hackernewsgithubprojects

📦 raymondhuang210129/llama.cpp-adaptive-kv-streaming

Run Massive LLMs on Small GPUs

This fork of Llama CPP lets you run massive language models on tiny graphics cards by moving the memory burden to your computer's main memory. Normally, long conversations require huge amounts of video memory, causing small cards to crash, but this version intelligently streams data between your hard drive and graphics card in real time. It keeps your GPU busy without freezing, allowing a twenty-seven billion parameter model to run fully on just sixteen gigs of video memory. This is a huge leap for anyone who wants local AI without buying expensive enterprise hardware, proving that smart software can beat raw hardware limits.

🆔 @hackernewsgithubprojects

📦 stanford-tml/robot_keyframe_kit

Robot Keyframe Kit: The Universal Robot Animator

Robot Keyframe Kit is the tool that finally lets any researcher animate any robot without writing code. It plugs into MuJoCo, the standard physics engine for robotics, and gives you a simple visual interface to pose, move, and save a robot’s motion. The standout feature is its mirror mode: move one arm, and the opposite arm mirrors the motion with the correct joint directions handled automatically. That single feature turns hours of manual tweaking into seconds of intuitive design. It’s built for speed, works with any standard robot model, and hands you clean, playable motion data ready for research or simulation.

🆔 @hackernewsgithubprojects

📦 pedrovieira/holeberry

Holeberry: Control Pi-hole from your Mac Menu Bar

Holeberry lets you unblock the specific website you are viewing without turning off your entire network’s ad blocking. It is a native macOS menu bar app that acts as a remote control for your Pi-hole instances, saving you from opening a browser tab every time you need to check stats or tweak settings. The coolest feature is its smart browser integration; it detects the domain in your current tab and allows you to unblock just that one site with a single click. This keeps the rest of your network protected while fixing your immediate issue.

🆔 @hackernewsgithubprojects

📦 anemll/dspark-vllm-gx10

DSpark: Run DeepSeek V4 on Two Desk-Top GPUs

DSpark is the two-node setup that finally makes massive AI models runnable on compact desktop hardware. The main project, DSpark vLLM for two DGX Spark nodes, solves a specific hardware problem: the DeepSeek V4 model is simply too big to fit on a single compact computer, but it runs smoothly when you connect two of them. This repository handles the complex technical setup required to bridge the software and hardware, ensuring the system actually works without crashing. It includes a live dashboard so you can watch performance in real time and provides a fully reproducible deployment process.

🆔 @hackernewsgithubprojects

📦 roadmaus/comfyui-continuity

One Node for All Your AI Video

Render finished AI videos with sound using one single node inside ComfyUI. The Continuity pack strips away the complex wiring and lets you just type a prompt, attach reference images, and hit render. It handles the heavy lifting for six different model families, driving them entirely locally without any API keys or cloud costs. This solves the headache of managing separate workflows for each new model by putting everything in one place. You get the raw creative freedom of open source tools with the simplicity of a single button.

🆔 @hackernewsgithubprojects

📦 amirmushichge/machine-vision

Turn Any Video Into Generative Art with Machine Vision

Machine Vision transforms your local videos into dynamic, generative graphics right in your browser without sending a single frame to a server. It analyzes motion, edges, and light in real-time, then overlays a deterministic field of points, lines, and labels that react to your footage. The coolest part is the privacy: everything stays on your device, letting you experiment with a completely private, creative coding playground. You can tweak the chaos, pick presets, or fully randomize the look, then export a five-second composite clip in seconds.

🆔 @hackernewsgithubprojects

📦 vrgamegirl19/vrgdg-seedvr2-tensorrt-studio

Fix Old Videos Locally with SeedVR Studio

Restore blurry videos without sending them to the cloud. This local tool uses your computer's graphics card to repair and upscale footage, giving you a real-time preview so you can compare the before and after side by side. It is fast enough to handle long clips, and if your render stops, you can pick up right where you left off. It is the perfect way to breathe new life into old home videos or rough game footage, all while keeping your data safe. Just drop in a clip, tweak the settings, and let your GPU do the heavy lifting.

🆔 @hackernewsgithubprojects

📦 alpbahadur/49-ide

49 Agents IDE: The 2D Canvas for AI Terminals

Forget terminal tabs. 49 Agents IDE replaces your cluttered command line with a zoomable, infinite canvas where every terminal lives side by side. You can arrange panes spatially, zoom out for the big picture, and watch AI agents work across multiple machines without ever touching SSH. It’s like a living map of your entire coding setup, accessible from your laptop or phone. Instead of alt-tabbing through hidden windows, you see everything at a glance, with live stats and file editors right on the surface. It turns chaotic agent management into a calm, visual workspace that actually fits your workflow.

📰 https://news.ycombinator.com/item?id=49514828

🆔 @hackernewsgithubprojects