303 subscribers
14.1K videos
14.7K links
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ tabooharmony/roblox-brain

roblox-brain

roblox-brain gives coding agents 29 ready-made Roblox skills, with quick notes plus deep references, so they can build, fix, and ship Roblox games instead of guessing. Think of it as a cheat sheet for the whole Roblox Studio workflow, from Luau code and networking to mobile menus, physics, analytics, and launch checks. The useful part is progressive: the agent first reads a short summary, then opens the long reference only when it needs detail. That makes help practical without drowning the model in trivia. It is not a game engine or a plug-in; it is a library of verified guidance for agents.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ w01fb0ss/pibot

PiBot: Your Desktop AI Team

PiBot gives you a whole AI team running right on your own desktop, and it actually uses your computer like a coworker. Instead of one chatbot, you get group chats where different agents take on different roles, then do real work across your files, browser, and apps, with approvals so nothing scary happens without asking first. It is local-first, so your work stays closer to your machine, and it runs on macOS, Windows, Linux, and Android. The cool part is that it feels less like a tool and more like a tiny office you can boss around.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ frrazer/roblox-game-boilerplate

Frazer's Game Boilerplate

Frazer's Game Boilerplate is a ready-made Roblox setup built to help AI agents build games without guessing. It comes with Rojo, Wally, typed Packet networking, ProfileStore data, strict Luau, and an AGENTS.md guide, so the first thing you see is a clean project structure instead of a blank place. The clever part is that it turns the boring setup work into a repeatable workflow: agents can install the tools, sync code through Rojo, and follow strict rules for naming, data, and client-server boundaries. That means a new game can start with a clear map of where code lives and how systems are meant to talk.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ msayib/roblox-dev-skill

Roblox Dev Skill

Roblox Dev Skill turns an AI coding assistant into a Roblox expert that writes current, strict, tested Luau instead of guessing. It loads 14 reference guides, worked examples, and a local API lookup so your agent can build, debug, secure, and sell Roblox features with server authority and anti-exploit habits. The catch is that it is a knowledge base, not an MCP server, so Studio access still comes from Roblox's built-in tooling. It is useful because it keeps the agent honest about what actually works in today's engine, and it says so when something is beta or not enabled.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ makenotion/claude-code-notion-plugin

claude-code-notion-plugin

claude-code-notion-plugin is the plug-in that turns Claude Code into a Notion powerhouse. Instead of juggling your workspace in a separate app, Claude can search, read, create, and update your Notion pages, databases, and tasks with one-click install. It bundles twelve Notion skillsβ€”like database design, meeting intelligence, and weekly digestsβ€”alongside a secure server and handy slash commands. The coolest part? You can hand Claude a task link and watch it plan, build, and even explain its code changes right inside Notion. It feels less like a tool and more like a teammate who actually knows your workspace.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ ronglecat/grok-bot-clipper

Grok Bot Clipper: Capture Web Pages for Your BOT

Grok Bot Clipper turns any web page into a clean, ready-to-send package for your Grok Bot. It is an unofficial browser extension built for people who want to grab a link, a screenshot, or a social post and hand it to an AI assistant without wrestling with copy-paste. The core trick is a simple capture and collect flow: you can select text, take a screenshot, or grab a social post from sites like X, Xiaohongshu, or Douyin, then drop it into a material basket with other sources. Before anything goes out, you can edit the draft, add instructions, and preview exactly what the BOT will receive.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ snapetech-org/slskdn

slskdN

slskdN is a web interface and daemon for Soulseek file sharing. It turns a classic file-sharing program into a browser-friendly control panel with search, browsing, transfers, and background wishlist-style acquisition workflows. The stable core is reliable single-source transfers, while extra systems like mesh networking, federation, and multi-source downloads are still experimental. The interesting part is that it adds a polished control plane around the Soulseek experience, not just a raw client, but you should check feature maturity before trusting the flashy extras. If you want Soulseek with a modern web dashboard, slskdN is worth exploring.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ melvynx/video-agent-skills

Video Agent Skills

Turn a raw phone take into a finished, polished video without touching a single editing app. Video Agent Skills helps creators script, research, and edit short-form videos like YouTube Shorts, TikTok, and Instagram Reels right inside Claude Code, keeping everything local on your computer. The standout feature is its short-editing engine: you record a take, drop it into a folder, and Claude automatically cuts out silences, speeds the footage, adds punchy captions, boards that highlight key moments, and a call-to-actionβ€”all in a consistent, professional split-screen paper style. No fancy software, no subscription, and nothing goes out publicly without your explicit approval.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ awslabs/codekb

CodeKB

CodeKB is the code-understanding tool built for autonomous software factories. It reads your repositories, maps how they fit together, and hands that knowledge to your AI agents, so they stop guessing and start knowing what a change will touch. Instead of hand-picking repos for every task, you describe the task and CodeKB finds the right ones, then powers a chat agent and semantic search that actually understand the code. It is built around spaces, which are snapshots of one branch or tag, and hyperspaces that group related repos so the whole system can be searched at once.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ ontogr/agentic-graphrag

Agentic GraphRAG

Agentic GraphRAG builds one graph that links enterprise knowledge to the conversations and decisions your agents make. Every decision points back to the exact passages and task events behind it, so an agent can revisit earlier choices with their proof, pick up unfinished work across sessions, and get flagged for review when a source changes. A citation check even catches a source an agent never read. This matters because agents usually forget their own reasoning, and this keeps the trail visible. It runs on Python with Neo4j or FalkorDB, and vectors can live in the graph or in Qdrant, Milvus, or Weaviate.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ cryptoyuyyy02/stickman-video-director

Stickman Video Director

Stickman Video Director turns a topic into a finished stick-figure story video, from the first scene to the final cut. It is built for people who want a punchy short video without wrestling with every tool. The interesting part is the split between two engines: a model engine that draws smooth, continuous scenes and a code engine that renders frame by frame with no video budget. The author tested both, and settled on the model route for final pieces, with the code route as a free, controllable test path. For a curious developer, that means you can get a rough draft fast and then polish the good version.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ rohanarun/alpoge-rh-replay

Alpoge Rh Replay: Checking a Big Math Claim Together

Alpoge Rh Replay is an independent crowd-sourced replay of a claimed Lean proof of the Riemann Hypothesis, with 175,187 module tasks and 2,858 work packets to build and check. The repository does not claim a finished full verification; the pilot transferred 150 modules and one downstream module was kernel-checked, so the takeaway is that the proof is being checked openly, piece by piece, by volunteers rather than trusted in one leap.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ aaryanverma/inkrail

Inkrail β€” a typewriter that actually feels like one

Inkrail is the quiet, offline typewriter app that makes writing feel like paper, ink, and a little room to breathe. It turns your Mac or Windows computer into a warm desk where letters appear on textured paper instead of a sterile screen. What makes it clever is the moving machine: as you type, the capsule and rail glide along below your words, like a real typewriter. You can choose paper, ink, fonts, lamps, sounds, and desk scenes, then switch to Focus Mode for a wider page and a calmer view. It saves locally, works offline, and is completely free, no accounts or subscriptions.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ t21dev/turbo-reader

Turbo Reader: A Tiny RSS Reader That Actually Works

Turbo Reader is a desktop RSS reader with an installer under five megabytes that opens in under half a second and holds twenty thousand articles in a fourteen megabyte core process. Most feed readers open like a junk drawer, but Turbo Reader opens on what happened since you last looked, with counts for today, this week and this month, pinned feeds first, and a section per category. It ranks articles locally with no account and no API key, using freshness, what you read, which feeds you actually open, and your own interest and mute lists.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ tabulai/mlx-learn

mlxlearn

mlxlearn runs scikit-learn-style classical machine learning on Apple silicon with the Metal GPU, and it can make clustering and nearest-neighbor search dramatically faster. The idea is simple: normal machine-learning code stays familiar, but the heavy work moves onto a GPU built into an M-series Mac. It is useful for people who want quicker fits without rewriting their project or learning a new modeling language. The concrete win is visible in clustering: k-means++ seeding for 8,192 centers on MNIST takes about 5.4 seconds instead of 217 seconds, while still matching scikit-learn's chosen starting centers for the same random seed.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ kevinpbuckley/vibe3d

Vibe3D

Vibe3D turns Unreal Engine's Modeling Mode into an API an AI agent can drive. Instead of clicking through a cluttered viewport, a connected agent can create a mesh, shape it, unwrap it, bake it, rig it, and save it as a static or skeletal mesh without ever touching a gizmo. It is useful because it lets a computer build real 3D assets the way a designer would, just faster and repeatable, with a built-in agent skill teaching the agent exactly how the whole workflow fits together. The cool part is that it feels like handing an AI the keys to a full 3D workshop inside Unreal.

πŸ†” @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
πŸ“¦ taucetiproject/taucetiroadmap

Tau Ceti Roadmap: The Map for Human-Checked Math

Tau Ceti Roadmap is a human-controlled map of math goals for Tau Ceti, an AI-welcoming Lean library built on Mathlib. Its one clear capability is turning big proof projects into tracked folders with status and progress notes, so anyone can see what is planned, done, or still open. That matters because machine-written math still needs human review, and this makes that review visible. Instead of guessing whether a library is finished, you can open the roadmap and read the trail. The takeaway: this is not just a list of math topics, it is a public checkpoint system for keeping formal proofs honest.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ dnotitia/dna-factory

DNA Factory

DNA Factory is the one-YAML toolkit that trains language models without turning your weekend into a config maze. It handles the usual post-training work β€” teaching a model from examples, tuning it on good versus bad answers, and rewarding what it does well β€” all with the same simple setup. The neat trick is that every method shares one training flow, so you write one config and change the method, instead of juggling five separate pipelines. It even checks the results while training is still running, so you can watch progress without stopping the show.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ jasnell/node-skills

Node Skills: Teach Coding Agents New Node.js

Node Skills gives coding agents a cheat sheet for brand new Node.js features that they were never trained on. It covers the latest built-in modules, APIs and flags, changed defaults and removals since Node.js 24 LTS, so your assistant won't guess wrong or reach for an old npm package. Every skill is written from pinned official docs and verified by runnable examples, and it works in tools like Claude Code and opencode. Think of it as a tiny, trustworthy field guide for the newest JavaScript runtime. Install it as a plugin and your agent actually knows the present, not the past.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ ruoyiqiao/mjlab_hand

mjlab_hand: Teach Hands to Juggle

Watch a simulated hand pick up a ball and start juggling. mjlab_hand is a training playground for dexterous robot hands, where you can teach virtual fingers to grasp, twist, throw, spin a plate, or juggle three balls at once. It brings together several hand models, including Allegro, LEAP, Shadow, Sharpa, Wuji, and XHand, so you can test the same moves across different designs. The cool part is that it is built to learn through trial and error, rewarding the hand for making new contact with objects instead of just hitting the target. If you are into robotics, you will see how messy physics turns into a neat skill.

πŸ†” @hackernewsgithubprojects