📦 danjdewhurst/story-skills

Story Skills: The Continuity Engine

Story Skills catches dead characters walking, unfired Chekhov guns, and payoffs that land before their setup before a reader ever could. It’s a set of agent skills that gives AI writing tools a shared, plain-markdown format for your entire story bible, including character files, worldbuilding notes, and plot arcs. But the real magic is the companion command line tool that treats your story like code. It runs a deterministic continuity engine that checks for contradictions exactly like a compiler treats type errors. If your files are well-formed but the plot doesn’t hold together, it flags the exact file and line.

🆔 @hackernewsgithubprojects

📦 gentleman-programming/gentle-shell

Gentle Shell: The Architect's Terminal

gentle shell turns your terminal into a controlled workspace where you direct your coding agent instead of just typing commands. It solves the problem of messy, unstructured AI coding by giving you a single place to see active tasks, track changes, and review evidence. The most interesting part is how it acts like a senior architect; it doesn't just write code, it plans, verifies, and shows you exactly what it did so you can trust the result. If you want your AI helper to feel like a reliable colleague rather than a random text generator, this is the tool that makes that possible.

🆔 @hackernewsgithubprojects

📦 local-inference-lab/b12x

Run DeepSeek on Your RTX 5090 with B12X

Run DeepSeek V4.1 on your RTX 5090 or DGX Spark. B12X is a kernel library that turns consumer Blackwell cards into a local inference machine. It handles the low-level math for attention and experts, letting you serve large models right on your desktop. No datacenter needed. If you want to run serious AI on your own hardware, this is your shortcut. Grab B12X and start experimenting with local models today.

🆔 @hackernewsgithubprojects

📦 superagents-lab/jev-search

Jev Search: The Search Engine That Thinks First

Jev Search doesn't just find pages; it actually figures out what you're trying to ask before it even starts looking. It uses an AI helper to pick the right websites and time frames, then sends your question to engines like Google and DuckDuckGo at the same time. The coolest part is that it ranks the results by relevance and shows you exactly why it picked them. It’s like having a smart librarian who knows where to look and sorts the books by how useful they are. No more digging through ten tabs to find one answer. This is a cleaner, smarter way to search the web.

🆔 @hackernewsgithubprojects

📦 autonomous-ai/openharness

OpenHarness: The Desk Device for Coding Agents

Transform any coding assistant into a specialized engineer that designs circuit boards, models three dimensional parts, and builds playable games right on your screen. The platform runs these agents in persistent terminals across all your computers, ensuring your projects continue working even after you close the application window. The standout feature is the open hardware desk device that plugs into your setup, giving you a tangible way to manage and interact with these digital workers. It connects everything through secure, encrypted channels without needing complex network configurations. This creates a focused environment where you can chat with an agent while watching your digital creations take shape in real time.

🆔 @hackernewsgithubprojects

📦 sstraus/tuicommander

TuiCommander: The IDE for AI Agents

TuiCommander is the integrated development environment that finally lets you run multiple A.I. coding agents on separate branches without losing your place. It spins up isolated workspaces so each agent works in its own lane, meaning you can watch them code, test, and commit in real-time without them stepping on each other's changes. Instead of juggling a dozen terminal windows or losing track of what is happening, you get a single dashboard showing exactly what each agent is doing, along with live diffs and pull request statuses. It turns the chaos of parallel A.I. coding into a clear, manageable workflow where you stay in control.

🆔 @hackernewsgithubprojects

📦 nandhakishorm/laya

Laya: The Fastest Way to Make AI Decisions

Laya lets you ask an AI to judge a situation and get a firm, reliable answer in milliseconds. It skips the slow part where language models invent words and instead looks at the facts to pick a clear label or score. Think of it like a super-fast triage nurse for your data. It instantly tells you if an email is billing, if a comment is toxic, or if someone is about to quit your service. The coolest part is that its confidence scores are actually mathematically accurate. That means if it says it is ninety percent sure, you can trust that number completely.

🆔 @hackernewsgithubprojects

📦 jaredpalmer/kev

Kev: AI Decision-Making on Your MacBook

Make any small laptop run a sophisticated AI decision engine that spits out calibrated probabilities instead of vague text. Kev is a compact model that reads a document once and answers multiple typed questions in parallel during a single fast pass. Instead of generating sentences, it scores your specific options against the text, giving you a precise number for how confident it is in the answer. It runs entirely locally on an Apple chip, meaning your data never leaves your machine. You get a private, highly accurate tool that classifies complex inputs without the lag or privacy risks of cloud servers.

🆔 @hackernewsgithubprojects

📦 kitze/unclutter

Unclutter: The AI Browser Extension That Cleans Web Clutter

Unclutter is a browser extension that uses an AI model to identify and hide ads, cookie banners, and pop-ups on any website. The surprising part? It does not delete anything; it just reversibly hides clutter so your main content remains visible. Once a page is analyzed, the rules are saved as reusable templates. This means similar pages, like different news articles on the same site, automatically load the same clean view without needing to re-analyze them every time. It is a simple, local tool that brings back the days of clean reading by stripping away the noise while keeping your data private.

🆔 @hackernewsgithubprojects

📦 decisionbox-io/decisionbox-platform

DecisionBox: The AI That Finds Data Insights Alone

DecisionBox is the autonomous data discovery tool that finds insights without you asking a single question. It connects to your data warehouse and lets an AI agent decide what to investigate on its own. The agent writes and runs dozens of SQL queries to explore your data, then verifies every finding with independent checks to ensure accuracy. You get validated insights and ranked recommendations in your dashboard, all while keeping your data and infrastructure under your control. If you want to know what your data is trying to tell you without writing code, this is the tool to try.

📰 https://news.ycombinator.com/item?id=47875097

🆔 @hackernewsgithubprojects

📦 bespokelabsai/nimble

Nimble: Fast AI Decisions Without Reasoning

Nimble is the local AI model that answers complex questions instantly without writing out any reasoning. Instead of generating a long paragraph to explain its thought process, it reads your text once and simply picks the correct answer from a list you provide, making it blazing fast for tasks like routing requests or checking conditions. The real trick lies in how the team trained it using contrastive data curation, where they create nearly identical examples that differ by just one fact to teach the model exactly which details matter.

🆔 @hackernewsgithubprojects

📦 webprodigies-org/flute

Turn Your React UI Into a 3D Movie

Transform your live React interface into a cinematic three-dimensional video using Flute by Web Prodigies. This open source tool lets your coding agent compose camera angles, depth, and motion directly from your existing components, solving the problem of creating high-end promotional assets without rebuilding your app in a separate 3D engine. You keep your original styles and data while exporting high frame rate MP4 files entirely locally. It is a fascinating way to visualize your actual product in motion. If you build React apps, this is a powerful way to make your work feel dynamic.

🆔 @hackernewsgithubprojects

📦 mah3sec/forgeguardian

ForgeGuardian: The Offline Supply Chain Scanner

ForgeGuardian scans your software dependencies entirely on your own machine, meaning your code never leaves your computer to get checked for threats. It solves the problem of trusting the thousands of external packages you download to build your apps, catching hidden malware and fake packages before they sneak into your final product. The coolest part is that it runs offline, so you do not need to upload your secrets to a cloud server to stay safe. It gives you full control over your security without sacrificing speed. You get peace of mind knowing exactly what is inside your code. Keep your data private and secure. Try it today.

📰 https://news.ycombinator.com/item?id=49574041

🆔 @hackernewsgithubprojects

📦 moritzkremb/jev-voice-browser

The browser that acts before you finish the sentence

The browser starts typing your search query before you even finish saying the name of the person you are looking for. This project, called Jev Voice Browser, connects a specialized AI model to a real web browser. The model does not write code or plan actions. It answers a series of simple yes or no questions in about three hundred milliseconds. If it is confident you are done speaking, the browser acts immediately. If you are still talking, it waits. The text you search for is never generated by the AI. It is cut directly from your spoken transcript. This means the system is fast, cheap, and highly reliable.

🆔 @hackernewsgithubprojects

📦 devmortimer/pi-warden

pi-warden: The AI Safety Net You Didn't Know You Needed

Pi-warden prevents AI coding agents from making irreversible mistakes by checking every action against your project rules before execution. Instead of interrupting your workflow with constant approval dialogs, it quietly judges if a command is safe or off-track, then nudges the agent to fix its own work. In one hundred fifty controlled tests, projects with this guard active broke zero rules, while those without it failed six times. It acts like a seatbelt, catching dangerous deletions or unverified claims without stopping your momentum. You keep working while the agent self-corrects.

🆔 @hackernewsgithubprojects

📦 unicodef1wn/grokbot-field-notes

Grok Bot Field Notes: 72 Hours of Agent Failures

Grok Bot Field Notes is the practical handbook that turns seventy-two hours of live software chaos into reusable rules for your own coding agents. Three engineers from the xAI Grok Bot team built a product from scratch on stream, documenting every failure, from broken layouts to security leaks, to create a clear set of house rules you can drop directly into your repository. The core insight here is simple: verification is the real job, not just writing code, and every agent needs a specific way to prove its work before it is finished.

🆔 @hackernewsgithubprojects

📦 romanslack/jev-drone

Jev Drone: How a Small AI Model Pilots a Quadcopter

Fly a real quadcopter through a gauntlet of obstacles using just its onboard camera. Jev Drone shows how a lightweight judgment model can make high-level tactical decisions while simple code handles the twitchy, fast-moving safety reflexes. The coolest part is that without this small model, the drone gets stuck at the first wall because it cannot figure out how to fly over it. With the model in the loop, the drone climbs over barriers, times sweeping gates, and even re-acquires its target after losing sight in a dense cluster of pillars.

🆔 @hackernewsgithubprojects

📦 nekuda-ai/windtunnel

WindTunnel: The Browser Agent Benchmark

WindTunnel settles the debate on how AIs should actually control your web browser. It pits the new WebMCP standard against older methods, like having an AI stare at screenshots and click pixel by pixel. The project runs real, open-source websites in isolated containers and throws forty-nine specific tasks at different AI models. It then checks the actual database to see if the job got done. The surprising result? Giving the AI direct commands is dramatically cheaper and faster than letting it guess by looking at images. If you are building agents, this data tells you exactly which path saves you money and time. Stop guessing. Test it.

🆔 @hackernewsgithubprojects

📦 coldteadotai/abide

Abide: The Rule Enforcer for AI Coders

Stop letting your AI coder ignore your strict project guidelines. Abide hooks directly into tools like Claude Code to audit every single line of code your agent writes. It uses a specialized decision model to check your specific rules, like 'use Yup for validation,' in just three hundred milliseconds. If the agent breaks a rule, it gets an instant, automatic prompt to fix the error before moving on. This tool turns your text-based instructions into hard, technical enforcement, catching mistakes that standard linters miss. It is the difference between hoping your AI follows instructions and actually making it obey them.

🆔 @hackernewsgithubprojects

📦 openai/tunnel-client

Tunnel Client: Local AI, Private Access

Tunnel Client is the secure bridge that lets private AI tools talk to ChatGPT without touching the internet. Most local AI servers are locked behind firewalls, making them invisible to cloud assistants. This tool fixes that by creating a hidden, encrypted tunnel from your private machine to OpenAI's servers. You can now use your own local data and code with ChatGPT or Codex while keeping everything safely offline. It is the perfect way to enjoy powerful AI features without compromising your data privacy. If you want to connect your local AI to the cloud, this is your safe, private path.

🆔 @hackernewsgithubprojects