📦 copilotkit/openmuse

OpenMuse: The Personal Agent That Keeps Working

OpenMuse gives a computer to a personal AI agent that you can actually see working on your phone. The most striking part is not just that it browses the web, but that it can take over a live browser session if you need to intervene, then let it keep going. It’s essentially a digital intern that handles emails, runs terminal commands, and tracks goals while you watch it go. The project is built with CopilotKit and runs its own server, so you can dig into the source code and tweak the whole setup.

🆔 @hackernewsgithubprojects

📦 bevibing/tutor-skills

Tutor Skills: Your Personal AI Study Partner

Tutor Skills is the study assistant that turns your messy files into a personal quiz master. It takes any document, PDF, or codebase and builds a structured study vault inside your Obsidian app. The coolest part is that it doesn't just make notes; it actually quizzes you. It tracks exactly which concepts you know and which ones trip you up, then drills those weak spots until you get them right. It’s like having a patient tutor who knows exactly where you’re struggling. If you’re studying for an exam or learning a new codebase, this tool helps you focus your energy on what actually matters.

🆔 @hackernewsgithubprojects

📦 anthropics/claudeforfoundationmodels

Claude for Foundation Models: The Bridge You Didn't Know You Needed

Plug Claude directly into Apple’s new Foundation Models framework to drive it with the exact same session APIs you already use for on-device models. This package solves the headache of juggling separate clients for server-side logic by making Claude look like a native Apple model. The coolest part? If your chosen model politely refuses a tricky question, you can chain a fallback model that seamlessly picks up mid-sentence, so the user gets one smooth answer without even noticing the switch. It’s a clever way to keep your app logic simple while accessing Anthropic’s power. Stop writing custom glue code and start building apps that feel native to both worlds.

🆔 @hackernewsgithubprojects

📦 google-research/rrsi

RRSI: The Self-Improving Agent

Take a frozen AI model and watch it get smarter without changing a single weight. That is exactly what RRSI does. It treats the scaffolding around an agent as an evolving piece of software, tweaking prompts and memory until the system solves real coding and design tasks. The problem is simple: most agents forget how to handle new jobs after practicing on old ones. RRSI fixes this by adding strict rules that stop the system from cheating or overfitting. It is the closest thing to a self-improving robot we have, proving that better tools matter just as much as better brains.

🆔 @hackernewsgithubprojects

📦 nvlabs/grail

GRAIL

Train a robot to climb stairs without ever touching the real thing. That is exactly what NVIDIA’s GRAIL does. It takes 3D models and video clips to simulate humans moving and grabbing objects in the digital world. Then it teaches a robot brain to copy those moves. The coolest part? The robot can pick up items and climb actual stairs in reality, all from that fake data. It saves researchers from building a thousand test tracks just to learn one trick. If you want to know how robots learn to move without a physical teacher, this is the project to watch.

🆔 @hackernewsgithubprojects

📦 malevrigns/agent-jev

AgentJev: The AI Reflex That Doesn't Write Words

AgentJev is the tiny AI model that answers your questions without writing a single word. Usually, we ask big AI models to explain their decisions in full sentences, which is slow and messy. This project changes that entirely. You give it a messy state, like a stack trace or a code diff, and a simple question. Instead of typing out an answer, it runs through once and instantly gives you a probability for every option you listed. It’s like a reflex for your software, answering in milliseconds instead of seconds. It hits seventy-nine percent accuracy on the test set and saves a lot of time.

🆔 @hackernewsgithubprojects

📦 maneek21/deft

Deft: The Workspace Where AI Agents Work Like Colleagues

Deft lets you hire AI agents to handle real work right alongside your human team. Instead of treating AI as a separate chatbot, this self-hosted workspace puts agents into the same channels, tasks, and notes as your people. The coolest part is that agents like Defty can actually draft tasks for you based on your team’s shared knowledge. You review the proposal, approve it, and the task is created with full context attached. It’s a smart way to keep a clear record of what the AI did and why, giving you total control without losing the speed.

🆔 @hackernewsgithubprojects

📦 byk/loreai

Lore: The Memory That Compounds

Lore is the AI memory system that stops your coding agent from forgetting everything after the first hour. It sits quietly between your favorite coding tool and the model, acting like a smart secretary that remembers exactly which files you changed and why. Instead of just summarizing your chat into a vague summary that loses important details, it captures the specific facts and decisions you made. This means your AI can work on a project for days without getting confused or losing track. It even lets you review what your AI learned in a simple text file right inside your code folder.

🆔 @hackernewsgithubprojects

📦 ringlochid/oh-my-subagents

Oh My Subagents: The AI Team Manager

Oh My Subagents is the local orchestrator that finally stops you from babysitting AI agents. Instead of manually spawning and polling temporary tools, it manages them as a durable, accountable team with persistent state. The real magic is interruption recovery. If a session crashes or the internet blips, it doesn't start over from scratch. It remembers exactly where the work stopped and picks right back up. This turns fragile, one-off prompts into reliable, repeatable workflows. You get a structured team that actually finishes the job, not just a chat log that dies when the tab closes. It is the difference between playing with AI and actually managing it.

📰 https://news.ycombinator.com/item?id=49140789

🆔 @hackernewsgithubprojects

📦 unreallabsai/unreal-agent

unreal-agent

Build a coding agent that actually handles long-running tasks without freezing. Unreal Agent from Unreal Labs is an asynchronous framework that lets your AI run multiple commands simultaneously. Instead of waiting for one file read to finish before starting the next, it fires off independent jobs in parallel. This means your agent can inspect code, run tests, and process images all at once, dramatically speeding up complex workflows. It treats these tasks like background workers, so nothing blocks the main brain of your project. If you are tired of agents stalling on slow operations, this tool keeps everything moving. Grab the source code and start building smarter, faster software today.

📰 https://news.ycombinator.com/item?id=49805748

🆔 @hackernewsgithubprojects

📦 harnessrouter/systemoneharness

System One Harness: AI That Never Lies

System One Harness turns a new kind of AI model into a reliable worker that never invents facts. While most chatbots guess and hallucinate, this project forces the model to pick one specific action from a strict list of options, like choosing a button from a menu. It tracks its own confidence and refuses to act if it is unsure, meaning it will simply stop rather than make up an answer. This creates a perfect record of every decision, making it ideal for high-stakes tasks like banking or medical records where errors are not allowed. It is not about chatting; it is about precise, verifiable execution.

📰 https://news.ycombinator.com/item?id=49778358

🆔 @hackernewsgithubprojects

📦 awdqwdasdg/comfyui-spectrum-qwen2.1

comfyui-spectrum-qwen2.1

This ComfyUI plugin skips most of the heavy lifting in your AI image generator to cut render times by nearly three. Instead of calculating every single step from scratch, it learns the pattern of your current image and guesses the rest, letting you generate high-quality visuals in half the time without changing your settings. It works by predicting the hidden state of the diffusion model so you get faster results with fewer calculations, making it perfect for quick iterations. If you generate images with ComfyUI, this node is the fastest way to speed up your workflow while keeping quality high.

🆔 @hackernewsgithubprojects

📦 lkarlslund/laya.cpp

Run AI Decisions in Pure C++

Run complex AI decisions directly from C++ without Python overhead. Lay A C P P takes a modern language model and compiles it into a lightweight native executable that runs entirely on your GPU. It uses Vulkan and CUDA to process text with strict precision, ensuring every answer matches a Python baseline exactly. This is great because it strips away heavy dependencies, letting you serve fast, reliable logic directly from code. You get the speed of a native app with the accuracy of a standard model, all in one tiny tool.

🆔 @hackernewsgithubprojects

📦 zdragg/rotomdex

Rotomdex: A Terminal Pokédex

A fully animated, offline-capable Pokédex that runs directly inside your command line without a browser. Built in Rust with a no standard library constraint, it renders crisp pixel art and animated sprites using Unicode symbols, which is a neat trick for low-level performance. You can download the data once to browse completely offline, or connect to the API for live updates, all within a classic eighty by twenty-four terminal window. It turns your plain text console into a tactile, retro gaming interface, proving that modern software can still feel like a handheld device from the nineties.

🆔 @hackernewsgithubprojects

📦 daseinlabs/open-jev

Open Jev: Play Doom with a Local AI

Rank multiple text choices in a single pass using a local language model that runs entirely on your Apple silicon chip. Open Jev solves the problem of slow, cloud-dependent decision making by scoring pre-written options against a context without generating new text. Instead of waiting for a server, it calculates the likelihood of each answer locally, which is how it lets a four billion parameter model play Doom in your terminal. The engine reads the game state as text and picks the next move from a fixed menu of actions. You get instant, private, and surprisingly capable AI control right on your desktop.

📰 https://news.ycombinator.com/item?id=49737236

🆔 @hackernewsgithubprojects

📦 romshark/datapages

Build Full-Stack Web Apps in Go

Datapages lets you build complete web applications using only the Go programming language. Most modern web tools force you to manage two separate ecosystems: one for the server-side logic and another for the browser-side interface. This project removes that friction by bringing interactive frontend features directly into your Go backend. You write your server logic, define your data models, and handle user interactions all in one unified codebase. This eliminates the need to configure complex build tools or maintain separate JavaScript projects. The framework integrates with Datastar to handle state and events natively within the server code.

🆔 @hackernewsgithubprojects

📦 lordx64/phantom-kv

Phantom KV: The Model Patch That Isn't

Phantom KV is the tool that removes AI refusals without touching the model. Instead of hacking the software code, it injects a tiny, reversible memory patch that the AI reads like a conversation. You can swap this patch mid-chat to toggle between safe mode and unrestricted mode without restarting the app. It is clever because it uses the AI’s own attention to change behavior, leaving the original file untouched. When you are done, you simply delete the patch, and the system returns to exactly how it was. It is a clean, reversible way to test model boundaries without permanent changes.

🆔 @hackernewsgithubprojects

📦 aru-labs/lossless-memory

Lossless Memory: Never Summarize

Your AI assistant probably forgets exactly what you said last Tuesday night. This project fixes that by refusing to summarize anything. Lossless Memory stores every single word of your conversation exactly as it was spoken, tagging each line with a precise timestamp. When you ask about a specific time, it searches by time first and words second, returning the actual raw lines in order. It even remembers the current topic so the chat feels continuous, not like a fresh start. It runs locally on your own machine, keeping your data private and your memories intact.

📰 https://news.ycombinator.com/item?id=49786419

🆔 @hackernewsgithubprojects

📦 angelosha/uchiyomi

Uchiyomi: The Self-Hosted Manga Server That Downloads

Uchiyomi is the self-hosted manga server that finally automates your entire reading workflow. It combines a personal library and reader with a smart scheduler that automatically fetches new chapters from the internet. Think of it as a dedicated tool for tracking your favorite series so you never miss an update. You simply point it at your local files and trusted sources, and it handles the rest. This makes managing your collection on a home server incredibly easy. It is a great option for anyone who wants to keep their digital comic library perfectly organized and up to date.

📰 https://news.ycombinator.com/item?id=49441669

🆔 @hackernewsgithubprojects

📦 lhlgithub/threejs-architecture-effects

Three JS Architecture Effects

A fully three-dimensional Chinese clock tower builds itself brick by brick in a single interactive web page. This open source skill for code agents turns plain instructions into a working three dimensional miniature that assembles itself on screen. Instead of a flat image or a video file, you get a solid structure you can orbit, zoom, and scrub through time using a single slider. Every piece of brick, wood, and tile is generated procedurally, meaning no downloaded models or paid assets are needed to create the scene. The result is a living architectural model that feels physical and tangible.

🆔 @hackernewsgithubprojects