📦 theoleecj/semif-openjev

SemIf: Instant AI Decisions

SemIf is the decision engine that reads answers directly from the model without generating text. Instead of waiting for a chatbot to type out a sentence that software has to parse, it reads the raw probabilities for specific options in a single pass. This cuts processing time from five seconds to just one second, making it ideal for routing requests or checking evidence in real time. It runs on standard hardware and even in your browser, proving that open models can handle complex logic without proprietary services.

🆔 @hackernewsgithubprojects

📦 typesafe-ai/system-one-adapter-python

System One Adapter: Test Any LLM Like a Human Evaluator

System One Adapter is the testing tool that lets you swap any large language model into the TypeSafe evaluation framework without rewriting your code. Instead of relying on a single proprietary service, this library acts as a universal translator, allowing you to point your evaluation questions at OpenAI, Anthropic, or Gemini providers just like a plug-and-play adapter. This is incredibly useful for developers who need to compare the cost, speed, and intelligence of different AI models side by side to see which one actually understands nuance best. By keeping the evaluation logic consistent while changing the underlying engine, you can make data-driven decisions about which model truly fits your project.

🆔 @hackernewsgithubprojects

📦 y0usaf/pi-jev

pi-jev: The Bouncer for AI Agents

Your AI coding assistant is about to run a command that could wipe your project, and it has no instinct for danger. pi-jev fixes this by acting as a strict bouncer for your AI agent. Before it executes any risky action, it asks a specialized model for a simple yes or no answer on whether the move is destructive or out of scope. If the risk is too high, it stops the action dead in its tracks and asks you for permission. It’s not about blocking your AI, it’s about giving it a safety net so you can trust it with real work without holding your breath.

🆔 @hackernewsgithubprojects

📦 nestrilabs/virtio-nvgpu

virtio-nvgpu

Render inside a virtual machine at the exact same speed as bare metal, while sharing the same physical graphics card. This project lets a guest system run the real, unmodified NVIDIA drivers, bypassing the heavy translation layer that usually slows down virtual graphics. Instead of serializing every single draw call across the virtual boundary, it forwards the low-level driver commands once, letting the guest write directly to the host's memory. The result is stunning: a guest machine renders within two percent of the physical limit, costs nothing in extra processor power, and even encodes video on the GPU itself.

📰 https://news.ycombinator.com/item?id=49824864

🆔 @hackernewsgithubprojects

📦 vigozhao/ai-visual-prompt-cookbook

The AI Style Cookbook

You can copy a single text file and make an AI image generator paint exactly like a specific magazine or comic book. A new project called the AI Visual Prompt Cookbook collects over a hundred of these ready-made recipes. Usually, getting an AI to draw in a consistent style takes hours of testing and tweaking. This project solves that problem by packaging the perfect words into a simple file you can just copy and paste. It works with popular tools like Midjourney and GPT. The collection is updated daily, so there is always a new look to try.

🆔 @hackernewsgithubprojects

📦 freestylefly/wechatbridge

WeChatBridge: The Mac App That Feeds WeChat Chats to AI

WeChatBridge is the Mac tool that finally stops your WeChat history from rotting in the app. It taps directly into the native share menu so you can grab a chat export and blast it right into your favorite AI agents or local notes. The coolest part? It turns messy group threads into clean, readable files for you or your AI to analyze, all without uploading anything to the cloud. It is the perfect bridge for developers and note-takers who want to leverage their digital life. Give it a shot to see how easy it is to make your chats actually work for you.

🆔 @hackernewsgithubprojects

📦 kyotofin/tax-doc-classifier

tax-doc-classifier: Classify 261 Tax Forms for a Penny

Identify exactly which IRS form every page in your tax documents belongs to, instantly and for almost nothing. This tool uses a specialized decision model to look at a page and pick from 261 specific forms, giving you a high-confidence answer without training a single AI model. It replaces expensive and slower large language models with a setup that is thirty-four times cheaper and six times faster. The entire classifier is just a generated list of form descriptions, so it is easy to update whenever the IRS changes a document. It is a clever, low-cost way to automatically organize massive stacks of tax paperwork.

🆔 @hackernewsgithubprojects

📦 undefined-ui/second-brain-os

Second Brain OS

An AI agent that actually organizes your notes for you is finally here. Most people save articles, bookmarks, and ideas with the best of intentions, but the manual filing and linking gets boring fast, so the system dies. Second Brain OS solves this by letting an AI agent do the tedious work. It reads your raw dumps of clips and transcripts, turns them into clean, linked markdown pages, and then automatically updates your existing notes when new information arrives. This means your personal knowledge base compounds in value instead of just growing messy. The agent handles the deduplication and linking so you can just ask it questions later.

🆔 @hackernewsgithubprojects

📦 agricidaniel/compass

Compass: Your Life in One Folder

One folder, not ten apps, now runs your entire life. Compass turns a plain text note app into a living command center where your journal, tasks, habits, and writing all talk to each other. The coolest part is the AI assistant built right into the notes. It reads your daily reflections and offers help, but it never changes a single word without your explicit permission. This keeps your personal data safe while giving you a smart helper for planning and writing. It is a simple, powerful way to organize your thoughts without losing control. Stop switching tabs and start using one honest system that actually works.

🆔 @hackernewsgithubprojects

📦 wy-coliney/jev-browser-use

Jev Browser Use: The 10x Faster Web Agent

A new tool called Jev Browser Use makes AI agents browse the web up to ten times faster by splitting the job in two. Instead of asking your expensive AI model to think about every single click, this project lets a cheaper, specialized model handle all the repetitive navigation, scrolling, and button pressing. The main AI model then takes over only when it needs to type text or use its eyes to verify the result. This approach was built to speed up real-world work, like checking college application dashboards, by saving the smarter model for the thinking parts.

🆔 @hackernewsgithubprojects

📦 yibie/awesome-jev

Awesome JEV: The Curated List for Typed Decisions

Awesome JEV is the curated list that actually tracks real-world projects using JEV, the new system for making fast, typed decisions with AI. Instead of just chatting, these tools ask specific questions and get back concrete answers, like a score or a yes or no, which makes them way cheaper and more reliable for automating tricky tasks. You will see cool examples like browser extensions that filter ads or coding agents that pick the right tool instantly. It is not a pile of vague theory, but a hand-picked collection of working software that proves this approach works in the wild.

🆔 @hackernewsgithubprojects

📦 johnheibel/pdoomvideo

Pdoomvideo: The AI-Animated Music Video

A computer model wrote every line of code for a hand-painted music video without being told what scenes to show. This project turns lyrics into a two-minute watercolor cartoon where a small character grows from a monitor to planet size, acting out the song's jokes entirely through visual gags rather than text. The system plans its own storyboard, directs subagents to draw the characters, and renders the final frames directly into a movie file. It proves that software can now generate complex, stylized animation from just a song, offering a glimpse into how creative tools will operate soon.

📰 https://news.ycombinator.com/item?id=49839624

🆔 @hackernewsgithubprojects

📦 tencentarc/worldcrafter

WorldCrafter: Explore 3D Worlds from a Single Image

Tencent ARC has released WorldCrafter, a system that lets you fly through a 3D scene generated from a single image. The surprising part is that it remembers the world. Unlike standard video models that hallucinate new details as you move, this keeps the scene consistent as you explore. It uses an internal memory to understand the 3D space, so objects stay exactly where you left them. This is useful for game development and VR because it solves the problem of worlds falling apart when you look around. It turns a flat picture into a navigable environment.

🆔 @hackernewsgithubprojects

📦 mikehasa/golive-skill

GoLive Skill: Put Your AI App Live

Your AI coding assistant can build a whole app in minutes, but getting it to real users still means juggling hosting, databases, domains, emails, and payments. GoLive Skill is an open-source tool that solves this by inspecting your app, planning the exact changes needed, and asking for your approval before it touches anything. It uses your own existing logins to deploy everything on your own accounts, then verifies that it actually works. No hidden backend, no extra subscriptions, and no telemetry. If you want to take an agent-built product live without the usual setup headache, this is the tool to watch.

🆔 @hackernewsgithubprojects

📦 jkudish/jev-browser

Jev Browser: The $0.001 Web Agent

Jev Browser is the web automation tool that drives a real browser for less than two cents. It works by asking a specialized AI model to choose one single action from the elements on a page, rather than generating entire page structures from scratch. This approach allows the software to complete complex tasks, like finding a specific price or filling out a form, in just a few seconds. The result is a fully functional web agent that is fast, incredibly cheap, and easy to audit. It turns a difficult programming problem into a simple, low-cost utility.

🆔 @hackernewsgithubprojects

📦 qwenlm/qwen-live-harness

Qwen Live Harness: Your Realtime AI Sidekick

Qwen Live Harness lets you talk to your computer while it watches and listens. It acts as a realtime bridge that sees your screen, hears your voice, and delegates heavy lifting to background tools like code assistants. The coolest part? It remembers. It keeps long-term memory of your preferences and context, so you don’t have to repeat yourself. Imagine saying, "Watch this code and tell me if it breaks," and having it actually do that while you keep chatting. It’s like having a very attentive, slightly caffeinated intern who never forgets a detail.

🆔 @hackernewsgithubprojects

📦 nvlabs/skill2env

How Skill2Env Automates AI Training Tasks

A single command can turn a simple text description of a skill into a fully automated computer test that AI agents can solve. This project is called Skill2Env, and it solves a major bottleneck in training artificial intelligence. Usually, researchers have to hand-code complex scenarios to practice a new ability. Skill2Env uses an AI helper to automatically build those scenarios, complete with the instructions, the testing code, and even the correct answer key. It generates these practice problems in a standard format that other AI systems are built to understand. You can feed it a list of skills and it will churn out hundreds of training exercises overnight.

🆔 @hackernewsgithubprojects

📦 lakeday-org/perch

Perch: The Linter That Understands Code

Perch is the linter that actually reads your code to find bugs. While standard tools check your syntax, this tool uses an AI to understand what your functions are supposed to do, spotting logical errors like flipped conditions or missing null checks that regular linters completely miss. It parses your project structure, asks specific questions about how methods interact, and flags issues based on confidence scores. It is not just a spell checker for code, but a semantic scanner that understands context. If you want to catch logic bugs before they hit production, this is the tool you need to try.

📰 https://news.ycombinator.com/item?id=49840204

🆔 @hackernewsgithubprojects

📦 huiliyi37/tianshu-harness

Tianshu harness: The AI that remembers like you

Your coding bot suddenly stops acting like a dumb tool and starts acting like a partner who actually remembers your project. That is the core promise of Tianshu harness. Most AI assistants forget everything the moment you close the tab, but this project builds a memory system that decays naturally, just like a human brain. It uses a clever trick called pheromone decay to keep important context fresh while letting old noise fade away. This means the AI gets smarter over time without getting confused by irrelevant data. It is not just a chatbot; it is a cognitive framework for building AI that truly understands context.

🆔 @hackernewsgithubprojects

📦 han-1413141/dsh-cost-meter

The AI Cost Meter You Need

The DSH cost meter tracks every cent of your AI spending right inside your chat window. This plugin plugs into the DeepSeek Harness interface to show live costs per conversation, token usage, and account balances. It solves the problem of hidden AI bills by displaying exactly what each model costs, including peak and off-peak pricing windows. You can set budgets, see provider quotas, and get alerts before expensive peak hours start. The interface is bilingual, supporting both English and Chinese. If you use AI coding tools, this tool tells you what you are actually paying, so you can manage costs effectively without guessing.

🆔 @hackernewsgithubprojects