📦 well-made/comfyui-wan-svi2pro-flf

comfyui-wan-svi2pro-flf

comfyui-wan-svi2pro-flf is the ComfyUI extension that finally lets you generate multi-clip videos with absolute control over both the starting and ending frames of each segment. Usually, AI video generators suffer from massive visual drift, or they completely ignore where you want a clip to finish. This clever tool elegantly merges smooth motion continuity with hard-locked end frames, giving you seamless stitching across up to seven clips and beyond. By cleaning up conflicting motion data at the transitions, it keeps your scenes coherent and perfectly aligned without the dreaded ghosting. Grab this node to build long, stunning, multi-segment videos that actually go exactly where you tell them to.

🆔 @hackernewsgithubprojects

📦 abhinav1416/coding-platform

coding-platform

coding-platform is the competitive programming hub that brings intense real-time head-to-head coding duels to life. Instead of just solving problems in isolation, this platform pairs you with a rival for an instant matchmaking battle. Under the hood, a clever background coordinator pulls your submissions and matches them against external services without slowing down your interactive coding screen. It even integrates with Codeforces, tracking your live external submissions and pushing the status straight back to your dashboard via websockets. It is a brilliant, event-driven playground that proves how smooth and responsive a real-time multiplayer application can be.

🆔 @hackernewsgithubprojects

📦 mozilla-ai/otari

Otari

Otari is the self-hosted proxy server that finally keeps your AI costs and API keys under tight control. It acts as a single, universal gateway sitting between your apps and over forty different AI providers, translating everything into a clean, OpenAI-compatible endpoint. Instead of scattering your real API keys across different applications, you store them safely in Otari and hand out customized virtual keys to your users or apps. It automatically tracks usage and enforces strict budgets before a model is ever called, stopping runaway bills in their tracks. Spin it up locally to easily take full ownership of your AI stack.

📰 https://news.ycombinator.com/item?id=48810528

🆔 @hackernewsgithubprojects

📦 ruc-nlpir/arbor

Arbor

Forget linear AI coding assistants that lose track of what failed. Arbor is an autonomous research agent that outperforms Claude Code by over two times on the same compute budget. Instead of guessing blindly, it builds a structured hypothesis tree to run real experiments. It proposes ideas, edits code in isolated git worktrees, and only merges performance gains that actually survive held-out test data. If an experiment fails, Arbor abstracts the lesson upward so future attempts start smarter instead of repeating the mistake. It is like having a methodical research scientist running your optimization loops on autopilot.

🆔 @hackernewsgithubprojects

📦 jimparis/qr-font

qr-font

The experimental OpenType font that converts bracketed text into fully functioning QR codes right inside your text editor. Instead of relying on external scripts, qr-font compiles an entire QR encoder directly into the font's internal layout tables as a physical circuit. When you type bracketed text, the font uses thousands of clever contextual substitutions to parse the characters, calculate the Reed-Solomon error correction, and layer zero-advance glyph outlines to draw the correct matrix. It is an incredibly clever hack that turns a simple font file into a functioning computer, letting you generate live QR codes wherever you can change a typeface.

📰 https://news.ycombinator.com/item?id=48811048

🆔 @hackernewsgithubprojects

📦 smtimesiwndr/gdid-reversal

gdid-reversal

Microsoft's secret Windows tracking identifier, recently exposed in a federal cybercrime complaint, is actually just a glorified server-assigned passport number. The gdid-reversal project completely deconstructs this elusive fingerprint, debunking the viral myth that it is a 128-bit hardware hash generated from your serial numbers. By tracing the identity stack, the project proves your machine actually requests this 64-bit identifier from Microsoft's servers during setup, storing it in your registry where any local user can read it. If you want to see exactly how Windows tracks your device across updates, you can fetch your own unique identifier with a single, painless line of PowerShell.

📰 https://news.ycombinator.com/item?id=48811081

🆔 @hackernewsgithubprojects

📦 mediamolder/mediamolder

MediaMolder

You can now visually redesign and validate complex media pipelines without writing a single line of cryptic command-line code. mediamolder is a modern processing engine that wraps the raw power of FFmpeg inside an intuitive visual editor. Instead of wrestling with fragile terminal strings, you drag and drop video filters, audio nodes, and encoders onto a canvas to build your pipeline. It automatically validates your setup to catch errors before you run it and lets you drop in custom AI nodes like Whisper speech-to-text or YOLOv8 object detection. It is the perfect upgrade for developers who want visual clarity and reliable video automation.

📰 https://news.ycombinator.com/item?id=48201167

🆔 @hackernewsgithubprojects

📦 pentesterflow/agent

Agent

This terminal assistant acts as an autonomous offensive security partner that uses real pentesting tools while keeping you firmly in the driver's seat. Instead of letting an AI run wild on your network, it requires explicit approval before executing sensitive shell commands or sending HTTP requests. It uses local or cloud models to map attack surfaces, hunt for security gaps like broken access control, and write markdown reports complete with reproducible curls. The best part is its local memory system that actually learns from your mistakes and successful workflows over time, making it smarter for your next assessment. It is a brilliant way to supercharge your security workflow without losing...

🆔 @hackernewsgithubprojects

📦 kui123456789/cdk-redeem-only-extension

cdk-redeem-only-extension

The cdk-redeem-only-extension is a specialized Chrome extension built to automate the entire lifecycle of ChatGPT account registration, eligibility verification, and bulk promo code redemption. Instead of manually signing up, getting verification codes, and checking for trial eligibility, this extension automates a streamlined seven-step pipeline to register accounts, set passwords, and verify their trial status. Qualified accounts are automatically pooled, and if you import your promo keys, it systematically redeems them across separate payment channels without missing a beat. It is the ultimate hands-free setup for managing bulk accounts and maximizing code redemption without constant manual intervention.

🆔 @hackernewsgithubprojects

📦 neeeophytee/finding-unknowns-skills

finding-unknowns-skills

Your prompts are just maps, but the real codebase is the actual territory, and the expensive bugs hide in the gap between them. The finding-unknowns-skills repository is a brilliant set of eight installable Claude Code commands designed to hunt down your blind spots before you write a single line of code. It features clever tools like a change quiz you must pass before merging, a blindspot pass to catch hidden landmines in unfamiliar modules, and a prototype brainstormer to test ideas cheaply. It is the ultimate toolkit for making AI agents work with you to uncover what you do not know you do not know.

🆔 @hackernewsgithubprojects

📦 syntheticautonomicmind/sam

SAM AI

SAM is the native macOS app that finally runs powerful AI models completely locally on your Mac while keeping your personal data completely private. This open-source assistant lets you chat with documents, research web purchases, and even generate images using your own hardware through Apple Silicon acceleration. Instead of sending your sensitive files or private thoughts to distant servers, you can run offline models directly on your machine or easily switch to cloud providers only when you choose. It is a fully featured hub designed for everyday people who want smart, secure AI right on their desktop.

🆔 @hackernewsgithubprojects

📦 nesaminua/claude-code-lsp-enforcement-kit

claude-code-lsp-enforcement-kit

You can cut your Claude Code token usage by roughly eighty percent just by forcing the AI to navigate code like a real developer. When Claude wants to find a function, it usually defaults to running heavy text searches across your whole project, burning through thousands of tokens. This repository, called claude-code-lsp-enforcement-kit, fixes that by installing strict system hooks that physically block Claude from using generic searches on code symbols. Instead, it forces Claude to use precise language server protocols to pinpoint exact definitions instantly. It even sets up progressive gates that require a quick diagnostics check before letting the AI read your files.

🆔 @hackernewsgithubprojects

📦 alchemist-x/predict-raven

Predict Raven

An open-source AI agent named predict-raven is now trading autonomously on real-world events, marking the first continuously-running trading bot live on Polymarket. Built as an advanced forecasting framework, the system uses a core component called Market Pulse to independently gather information, estimate event probabilities, and trade the difference between its calculations and market odds. To ensure safety, it bypasses prompt engineering entirely, relying instead on hard service-layer risk controls like automatic stop-losses and strict bankroll caps. The same technology also powers a completely market-blind public forecaster, proving that AI can analyze complex world events and make independent predictions entirely on its own.

🆔 @hackernewsgithubprojects

📦 igorbarshteyn/athena

Athena Offline Voice Assistant

Have a natural, voice-to-voice conversation with an intelligent assistant running entirely on your own local hardware without any cloud lag or creepy telemetry. This project lets you run a fully offline, privacy-first voice assistant that speaks with genuine emotion, actually reads the feelings in your own voice, and remembers you across different sessions. It solves the annoying lag of typical voice systems by using a brilliant C++ pipeline with zero runtime Python, allowing you to interrupt it mid-sentence just like talking to a real friend. It is the perfect weekend project for anyone wanting a truly private, hyper-responsive AI companion.

🆔 @hackernewsgithubprojects

📦 keijiro/meshslicer

Meshslicer

Meshslicer is the Unity template that finally makes real-time 3D object slicing run at a blistering sixty frames per second. Instead of relying on slow, stuttery physics calculations, it uses an incredibly clever custom slicing engine powered by Unity's Burst compiler and Job System to instantly cut models in half. Drag a cutting plane through a complex object like a crate or a torus, and it immediately splits into two clean, separate meshes, automatically generating watertight caps over the holes. It even includes specialized Blender tools to prep your models for perfect slicing. It is an incredibly satisfying and optimized playground for physics-based slicing mechanics.

🆔 @hackernewsgithubprojects

📦 superagent-ai/gateway

Gateway

Your coding agents are no longer locked into expensive model providers. Built in Rust, gateway is a lightweight local proxy that lets tool-using coding assistants like Claude Code and Codex CLI run on any platform you want, from local Ollama instances to alternative APIs like DeepSeek and Kimi. It completely translates complex API payloads, tool calls, and streaming responses behind the scenes, making different systems think they are speaking to their native endpoints. Best of all, it protects your workflows with a clever safety guard that never triggers mid-stream fallbacks, preventing corrupted agent loops. Just point your clients to this single local binary and start coding.

🆔 @hackernewsgithubprojects

📦 svg-project/quant-videogen

Quant VideoGen

Compress the massive memory footprint of generating long AI videos by up to eighty-five percent without changing your model weights or sacrificing quality. This clever project tackles the heavy memory cost of long-horizon attention data during video generation by quantizing the temporary cache down to just two bits during inference. This simple step slashes the memory needed for this cache by about seven times, turning a massive hardware bottleneck into an afterthought. It works seamlessly across several popular open-source video models to let you run longer creations on much more modest hardware. Give it a try to experience incredibly efficient long-context video generation.

🆔 @hackernewsgithubprojects

📦 shannhk/llm-wikid

llm-wikid

Build a self-growing second brain inside Obsidian by dumping raw articles, tweets, and PDFs into a folder and letting an AI agent compile them. Instead of slow vector database lookups, llm-wikid uses an agent to auto-sort your clippings, fetch full web content, download diagrams, and compile structured wiki pages with active cross-references. It even runs bias checks to highlight conflicting viewpoints and data gaps. Every question you ask gets answered with citations and filed back in, making your knowledge vault smarter the more you use it. Hook up your favorite agent, clone the repository, and start building a highly organized personal encyclopedia today.

🆔 @hackernewsgithubprojects

📦 flavioadamo/openfit

OpenFit

The Fitbit desktop dashboard that finally puts your personal health data back in your own hands. OpenFit is a private, desktop-first app that pulls your activity, sleep, and heart metrics directly from Google Health into a beautiful, local interface. Instead of staring at empty charts, its clever layout completely adapts to only show the metrics your device actually recorded. It even includes a secure, local AI assistant to chat about your health trends without ever sharing your credentials. It is the perfect, secure way to visualize your fitness journey on a bigger screen over a morning coffee.

🆔 @hackernewsgithubprojects

📦 lzh-phd/topic-feasibility-screener

Topic Feasibility Screener

Turn a rough research idea and a raw dataset into a complete, visual academic dashboard. Topic-feasibility-screener takes your CSV or Stata file, brainstorms dozens of concrete research questions, and automatically searches real academic databases to find genuine literature gaps. Instead of just chasing tiny p-values, it runs rigorous statistical checks like panel fixed effects and parallel trend tests, blending empirical strength with actual theoretical backing to score and rank your ideas. It hands you a beautiful HTML report packed with interactive feasibility charts and structured research designs so you can instantly see which paper topic is actually worth writing.

🆔 @hackernewsgithubprojects

📦 keyvaluesoftwaresystems/agent-opfor

Agent Opfor

Agent-opfor is the open-source adversary emulation library that tests your AI agents and servers by actively attacking them before real bad actors can. It simulates realistic, multi-turn conversations and sneaky maneuvers, mapping directly to security standards to expose weaknesses in tools, prompts, and memory. The coolest part is how it lets you see behind the curtain. By plugging into your monitoring stack, the evaluator doesn't just watch what your agent says, it inspects every hidden tool call and database check to catch silent data leaks. It is an incredibly clever way to secure your AI.

🆔 @hackernewsgithubprojects