📦 datalab-to/omni_parse_bench

Omni Parse Bench: The Truth About Your Document Parser

Your fancy AI document parser just choked on a single spreadsheet. That’s exactly what Omni Parse Bench is built to catch. This project stops us from guessing how well these tools actually work by slapping over sixteen thousand specific yes-or-no checks onto nearly three thousand real pages. It doesn’t just ask if the text is there. It verifies if the table structure survived, if the math holds up, and if the layout stayed sane. You get one clear number per system that tells you exactly where it fails and what that failure costs you in real dollars.

🆔 @hackernewsgithubprojects

📦 emanuele-em/kanzo

Kanzo: The Kanban Board for AI Agents

Kanzo is the self-hosted kanban board that finally lets your coding agents work alongside you. It is a single four megabyte binary that runs on your own computer, meaning no servers and no accounts to manage. The coolest part is that it acts as a bridge between you and your AI tools. Your coding agents can grab tasks, move them to doing, and even comment on their progress directly on the board. You can watch them work in real time from your browser. It’s like having a shared to-do list where humans and robots actually collaborate.

🆔 @hackernewsgithubprojects

📦 typetheoryforall/fvjobs

FVjobs: The Job Board for Formal Verification

FVjobs tracks seventeen open roles in formal verification, a niche field where the most surprising fact is that it specifically records which proof stack each job uses, like Lean or Isabelle, so you know exactly if your skills match. The project solves a real problem: formal verification jobs are usually scattered across academic lists and general boards that have no idea what a theorem prover is. This board collects them in one place, telling you the proof tools required and whether you are legally allowed to take the role from your location. It is useful because it removes the guesswork from applying to a specialized job.

🆔 @hackernewsgithubprojects

📦 deadhead04/skilled

skilled: Test Your AI Skills

skilled is the testing tool that finally proves your AI agent actually works. It acts like a rigorous exam for your custom instructions, checking if your model handles edge cases correctly before you trust it. If you tweak the prompt or swap the model, this tool reruns the same tests to catch silent failures. It’s not just a checker; it’s an improver, guiding your agent to fix weak spots based on real evidence. Think of it as a safety net for your AI workflows. No more guessing if a change broke something. Just run the suite, see the results, and ship with confidence.

🆔 @hackernewsgithubprojects

📦 haydenschmitty/floorplan

Floorplan: Your Codebase, Mapped in Plain English

Floorplan is the code-mapping tool that turns your messy codebase into a living, plain-English floor plan. It works by letting an AI read your files and draw an interactive map where every part gets a human name, not a cryptic filename. The coolest part is that it connects your front-end buttons directly to the server code that handles them, even if they live in completely separate repositories. It also runs a health check to find forgotten passwords or security holes, giving you a one-click fix for each.

🆔 @hackernewsgithubprojects

📦 nvlabs/voloagent

VoLoAgent: The Robot Brain

Teach a robot to recover from its own mistakes by using a vision language model as a safety net. VoLoAgent acts as a smart middleman between a standard robot policy and the simulation, breaking complex physical tasks into smaller steps. The standout feature is its failure detection: if the robot drops an object or gets stuck, the system spots the error instantly and triggers a recovery, such as re-grasping the item, without human help. This turns a fragile automation script into a resilient agent capable of handling long, multi-step jobs. It is a clear look at how language models can make physical robotics more reliable and self-correcting.

🆔 @hackernewsgithubprojects

📦 hamsanders/soundbox

Soundbox: The Free Local Audio Studio

Soundbox is the local audio suite that finally lets you own your sound without the subscription trap. You know how every AI music tool wants your credit card and your data? This one just runs on your own graphics card, completely offline, with no account and no monthly fee. You describe a scene, like heavy rain or a breaking window, and it generates high-quality sound effects, music, and even full songs with lyrics right on your machine. It is built for people who want creative freedom without the corporate cloud, giving you a real desktop app where you can edit, mix, and export exactly what you need.

🆔 @hackernewsgithubprojects

📦 mcg-nju/autotavern

AutoTavern

A computer program now plays full games of Hearthstone Battlegrounds entirely on its own, without ever touching the live game servers. This repository, called AutoTavern, recreates the entire game in code so researchers can test how well artificial intelligence makes split-second tactical decisions. Instead of just watching a bot play, you can feed it specific tricky scenarios to see if it truly understands the rules or just guesses. It solves the problem of needing a real human player to practice against, giving scientists a safe, repeatable sandbox to teach machines complex strategy.

🆔 @hackernewsgithubprojects

📦 feimacode/open-design-agent-kit

Open Design Agent Kit: Professional UI for your AI Coder

Ditch the generic, flat code your AI assistant spits out by default. Open Design Agent Kit transforms your standard coding tools into professional-grade design engines, letting you generate interfaces that look polished and brand-ready. It works by feeding hundreds of specific design styles directly into your existing editor, so you get that high-end aesthetic without installing heavy desktop apps or juggling new API keys. The real magic is the variety: you can switch between the sleek look of Apple or the bold energy of Nike with a simple prompt. It’s essentially a massive library of visual rules that teaches your coder to think like a designer.

🆔 @hackernewsgithubprojects

📦 oxnw/ai-phone

ai-phone: The AI That Calls People

ai-phone is the phone daemon that actually picks up the phone on your Apple Silicon Mac. It runs a full telephone agent locally, handling speech recognition, conversation logic, and voice synthesis without sending audio to the cloud by default. This solves the problem of having an AI that can genuinely place and receive calls, acting as a real assistant rather than just a text chatbot. It connects to standard phone systems, allowing it to book tables or handle inquiries with natural, low-latency responses. The standout feature is its fully local voice pipeline, meaning your audio data stays on your machine.

📰 https://news.ycombinator.com/item?id=50268009

🆔 @hackernewsgithubprojects

📦 beenuar/aisoc

AiSOC: The AI That Audits Itself

Turn raw security noise into auditable decisions with AiSOC, an open-source security operations center that you can run entirely on your own hardware. It stands out because every time an AI agent investigates a threat, it records its exact reasoning and tool calls in a replayable ledger. This means you don't just get a verdict; you get a transparent trail showing exactly how the model reached its conclusion. It solves the trust gap between fast AI analysis and human oversight, ensuring that no automated action happens without your final approval.

🆔 @hackernewsgithubprojects

📦 qf-studio/pilot

Pilot: The AI That Codes Your Tickets

Ship your backlog faster by letting an AI agent handle the actual coding. Pilot connects directly to your project tracker and takes a specific ticket, writes the necessary code, and opens a pull request for your team to review. It solves the bottleneck of waiting on developers for routine tasks, turning a simple issue into a concrete software change. You still keep control by reviewing the output before it merges, but the heavy lifting is done. It is a practical way to automate repetitive development work while keeping human oversight on the final result. Think of it as a tireless pair programmer that works from your task list.

🆔 @hackernewsgithubprojects

📦 iamrohithrnair/emeraldian

Emeraldian: Your Obsidian Vault in the Terminal

Emeraldian renders your entire Obsidian vault directly in your terminal, including live math, diagrams, and images, without a database. It reads your plain markdown files exactly where they sit on disk, so your notes remain simple text files even while the app is running. The most striking feature is its built in AI assistant, which edits your vault using the exact same commands you use, meaning you can watch every action it takes instead of trusting a summary.

🆔 @hackernewsgithubprojects

📦 botiverse/oar

One API For Every AI Coding Agent

OAR is the universal driver that treats every AI coding agent like a single, predictable tool. Instead of rewriting your app for each vendor, you write one program that speaks to all of them. The killer feature is live steering. You can interrupt a running agent, inject a new instruction mid-thought, and watch it adjust its plan in real time. This turns static chatbots into collaborative teammates. It also handles the messy logistics for you, like checking if an agent is logged in or how much quota you have left, all through one simple interface.

🆔 @hackernewsgithubprojects

📦 krusty84/yadisk-health

Yadisk Health: Verify Your Cloud Files

Yadisk Health is the disk utility that quietly checks if your Yandex cloud files are actually still downloadable. Many users assume their data is safe, but sometimes files become unreachable due to server issues or account quirks. This Python tool solves that mystery by grabbing the first kilobyte of every file in your drive to confirm it is there and readable. It does not touch your data or delete anything, but it gives you a clear report on what is working and what is failing. You can run it with a simple window or from the terminal.

🆔 @hackernewsgithubprojects

📦 jamesmontemagno/tiny-clips

Tiny Clips: The Menu Bar Recorder That Makes GIFs

Tiny Clips is the lightweight menu bar app that lets you turn any part of your screen into a polished video clip or animated GIF. It sits quietly in your system tray, waiting for you to highlight a specific region on your monitor. Once you do, it captures that exact area as a high-quality video or a lightweight GIF, handling the heavy lifting of compression and encoding in the background. This solves the common frustration of needing a quick visual demo without installing bloated editing software.

🆔 @hackernewsgithubprojects

📦 cd1s/safarier

Safarier: The Browser That Hides in Plain Sight

Safarier runs Apple’s actual Safari engine, so websites cannot tell your custom setup apart from a standard Mac. Most tools fake your hardware with scripts that get flagged instantly, but this app uses the system’s native privacy shield to protect your identity naturally. It is built for people who need dozens of isolated accounts without juggling extensions. The built-in proxy routing automatically matches your language and time zone to your exit location, making each session look like it comes from a real, specific machine. If you are managing multiple accounts, this is the cleanest way to do it without getting caught.

🆔 @hackernewsgithubprojects

📦 jacke-pp/open-yoki

Meet Open Yoki: Your AI Live Stream Host

Run a live stream where an AI host speaks with a cloned voice and moves a real-time digital face while reading chat and keeping a diary. Open Yoki solves the problem of high-maintenance broadcasting by handling the schedule, memory, and social media posting on a single server. The most surprising part is that this virtual host actually remembers returning viewers and writes personal notes about them in plain text files. You get a fully autonomous streamer who manages her own posts and interactions without needing manual input for every message. This gives you a reliable, low-effort way to broadcast content that feels personal and connected.

🆔 @hackernewsgithubprojects

📦 zeabur-oss/zeabur

Zeabur: Your Own Kubernetes PaaS

Zeabur gives you a familiar, easy-to-use interface for deploying applications, but instead of renting a cloud service, it runs directly inside your own Kubernetes cluster. It acts like a layer of translation, taking your standard Kubernetes setups and presenting them as simple projects with clear names and visual maps. The most striking feature is how it handles problems. When a service crashes or a node runs out of memory, Zeabur does not just show raw error codes. It explains exactly what went wrong in plain, everyday language and tells you precisely what to do to fix it.

🆔 @hackernewsgithubprojects

📦 lalalune/pumpfun-source

The Source Code of Pump.fun

pumpfun source is the reverse engineering project that fully reconstructs the hidden smart contracts of the popular Solana trading platform. This repository takes the compiled machine code from the live network and painstakingly rebuilds it into readable Rust source code. The most striking part is that it now matches ninety nine point five percent of the original functions, with three major programs reproducing their exact output. This transparency allows developers to understand exactly how fees and trades execute on the backend. It turns an opaque financial system into an open, inspectable codebase.

🆔 @hackernewsgithubprojects