302 subscribers
14K videos
14.7K links
Download Telegram
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
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ illumina/cellularai

CellularAI: Predicting Single-Cell Responses to Genetic Perturbations

CellularAI predicts how cells respond to genetic changes, turning a set of control cells in a new setting into realistic single cells for each perturbation. It takes control cells and a list of genetic perturbations, estimates how those cells react, and generates integer-count cells for every target. The method uses precomputed training summaries from the Illumina Billion Cell Atlas and public CRISPRi Perturb-seq datasets, then pools effects weighted by how similar training controls are to the new context, decides which genes respond, refines those effects, and synthesizes the cells.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ pierridotite/mobile-agent-testers

Mobile Agent Testers

Mobile Agent Testers sends 20 AI agents to test an app on 20 different phones in parallel, for free. Each agent plays a persona like an iPhone SE in Swedish or a Pixel 7 at 200 percent text, uses the app like a new user, and writes a bug report with screenshots. In one real run, 20 agents found 46 distinct bugs in a popular Flutter app, including a message dialog that overflowed by 149 pixels and hid the confirm button. No test scripts to write. It works with Flutter, React Native, Expo, and more, and the reports are encrypted so the logs stay private.

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

souldew

souldew turns PokΓ©mon SoulLinks into a live, no-spreadsheet session for two to four players on Mac, Windows, Linux or Steam Deck. Instead of shouting catches into a chat, you play your own legally obtained games in a built-in emulator while the app reads your team from memory and syncs everyone in real time over encrypted connections. A SoulLink means what you catch is tied to what your friends catch, and if one faints, the group goes down together. The cool part is the bookkeeping disappears: catches, deaths, routes and wipes show up automatically, with solo Nuzlocke mode, randomizers, ROM-hack patching, fast-forward with normal music, and OBS overlays for streamers.

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

Andon: One Person, A Whole Software Factory

Andon is the one-person software factory that keeps AI coding agents moving from idea to merge without dragging you in for every tiny step. Inside a single container cell, a coordinator agent reads a plain-file issue ledger, launches one worker agent per issue in its own git worktree, hands the pull request to a reviewer from a different model family, and lets a rule-based gate decide what can merge on its own. You only get called in when it is truly your call: what to build, how users should feel, promises to the outside world, irreversible risks, or changes to the line itself.

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

WineDroid: Android Apps on Your Desktop

WineDroid runs Android apps on web, linux, macOS and windows, like Wine for Android. Built in Rust, it executes DEX bytecode, implements Android framework behavior, and renders interfaces with Skia. Desktop builds use a Cranelift JIT, while the browser version uses the interpreter. Right now, apps like Weather Overview and Candle run with Gold and Silver ratings, though compatibility is still early and missing pieces are expected. It is an experimental compatibility layer, not a full virtual machine, and it shows missing APIs clearly instead of pretending they work. If you want to see how far it can go, try a browser demo or test a few APKs yourself.

πŸ†” @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ“¦ alesha-pro/maya-inkling-mini

Maya Inkling Mini

Maya Inkling Mini lets you run a huge, capable AI model on just one gaming GPU, giving you fast private chat with images and tool use in about 128 tokens per second. It works by keeping the most-used parts of the model in your graphics memory and swapping the rest from RAM or disk as needed. That means you can talk to a massive model on your own machine without sending data anywhere, all while it stays quick and responsive. You get a local, private assistant that feels fast, private, and practical, and it makes a big model feel like it belongs on your desk.

πŸ†” @hackernewsgithubprojects