Show HN: Keynot – Kill PowerPoint with HTML https://bit.ly/4cm4on7

Show HN: Keynot – Kill PowerPoint with HTML https://bit.ly/4tPn0Db April 15, 2026 at 03:05AM

Show HN: OpenRig – agent harness that runs Claude Code and Codex as one system https://bit.ly/4812UgQ

Show HN: OpenRig – agent harness that runs Claude Code and Codex as one system I've been running Claude Code and Codex together every day. At some point I figured out you can use tmux to let them talk to each other, so I started doing that. Once they could coordinate, I kept adding more agents. Before long I had a whole team working together. But any time I rebooted my machine, the whole thing was gone. Not just the tabs. The way they were wired up, what each one was doing, all of it. Nothing I'd found treats your agent setup as a topology, as something with a shape you can save and bring back. So I built OpenRig, a multi-agent harness. A harness wraps a model. A "rig" wraps your harnesses. You describe your team in a YAML file, boot it with one command, and get a live topology you can see, click into, save, and bring back by name. Claude Code and Codex run together in the same rig. tmux is still doing the talking underneath. I didn't try to add a fancier messaging layer on top. The project is still early. My own setup uses the config layer extensively (YAML, Markdown, JSON) for prototyping functionality that outpace what's shipped in the repo and npm package. But the core primitives are there and the happy path in readme works. It's built to be driven by your agent, not by you typing commands by hand. README: https://bit.ly/4sy2c1O Demo: https://youtu.be/vndsXRBPGio https://bit.ly/4sy2c1O April 15, 2026 at 12:46AM

Show HN: Mcptube – Karpathy's LLM Wiki idea applied to YouTube videos https://bit.ly/4cbiR6A

Show HN: Mcptube – Karpathy's LLM Wiki idea applied to YouTube videos I watch a lot of Stanford/Berkeley lectures and YouTube content on AI agents, MCP, and security. Got tired of scrubbing through hour-long videos to find one explanation. Built v1 of mcptube a few months ago. It performs transcript search and implements Q&A as an MCP server. It got traction (34 stars, my first open-source PR, some notable stargazers like CEO of Trail of Bits). But v1 re-searched raw chunks from scratch every query. So I rebuilt it. v2 (mcptube-vision) follows Karpathy's LLM Wiki pattern. At ingest time, it extracts transcripts, detects scene changes with ffmpeg, describes key frames via a vision model, and writes structured wiki pages. Knowledge compounds across videos rather than being re-discovered. FTS5 + a two-stage agent (narrow then reason) for retrieval. MCPTube works both as CLI (BYOK) and MCP server. I tested MCPTube with Claude Code, Claude Desktop, VS Code Copilot, Cursor, and others. Zero API key needed server-side. Coming soon: I am also building SaaS platform. This platform supports playlist ingestion, team wikis, etc. I like to share early access signup: https://bit.ly/4c9lC8r Happy to discuss architecture tradeoffs — FTS5 vs vectors, file-based wiki vs DB, scene-change vs fixed-interval sampling. Give it a try via `pip install mcptube`. Also, please do star the repo if you enjoy my contribution ( https://bit.ly/4vthsjo ) https://bit.ly/4vthsjo April 13, 2026 at 05:34PM

Show HN: Lint-AI by RooAGI, a Rust CLI for AI Doc Retrieval https://bit.ly/4tMnxpr

Show HN: Lint-AI by RooAGI, a Rust CLI for AI Doc Retrieval We’re RooAGI. We built Lint-AI, a Rust CLI for indexing and retrieving evidence from large AI-generated corpora. As AI systems create more task notes, traces, and reports, storing documents isn’t the only challenge. The real problem is finding the right evidence when the same idea appears in multiple places, often with different wording. Lint-AI is our current retrieval layer for that problem. What Lint-AI does currently: * Indexes large documentation corpora. * Extracts lightweight entities and important terms. * Supports hybrid retrieval using lexical, entity, term, and graph-aware scoring * Returns chunk-level evidence with --llm-context for downstream reviewer / LLM * Use exports doc, chunk, and entity graphs. Example: * ./lint-ai /path/to/docs --llm-context "where docs describe the same concept differently" --result-count 8 --simplified That command does not decide whether documents are in contradiction. It retrieves the most relevant chunks so that a reviewer layer can compare them. Repo: https://bit.ly/48N8l3d We’d appreciate feedback on: * Retrieval/ranking design for documentation corpora. * How to evaluate evidence retrieval quality for alignment workflows. * What kinds of entity/relationship modeling would actually be useful here? Visit: https://bit.ly/3UklysB https://bit.ly/48N8l3d April 13, 2026 at 08:11PM

Show HN: Bad Apple (Oscilloscope-Like) – one stroke per frame https://bit.ly/4sstEOA

Show HN: Bad Apple (Oscilloscope-Like) – one stroke per frame https://bit.ly/4dDKBSx April 13, 2026 at 06:01AM

Show HN: Local LLM on a Pi 4 controlling hardware via tool calling https://bit.ly/4cn6vHx

Show HN: Local LLM on a Pi 4 controlling hardware via tool calling https://bit.ly/3NYmxPZ April 13, 2026 at 12:14AM

Show HN: Stork – MCP server so Claude/Cursor can search 14k MCP servers AI tools https://bit.ly/4tqefjn

Show HN: Stork – MCP server so Claude/Cursor can search 14k MCP servers AI tools https://bit.ly/48KFXPd April 12, 2026 at 08:49PM

Show HN: Toy Python Lisp interpreters based on the 1960 McCarthy paper https://bit.ly/4dCFhPj

Show HN: Toy Python Lisp interpreters based on the 1960 McCarthy paper I wrote this set of Python files to try to help programmers understand the original LISP paper, assuming zero mathematical or Lisp knowledge. The original paper is a mind-blowing piece of computer science history for many reasons - I'd recommend anyone to try and get their head around it. I found plenty of fantastic LISP implementations which stay close to the original paper. But they are all fully-functional, practical implementations. The original paper builds from deeper fundamentals which it would be possible to write code in, albeit very impractical. I implemented these earlier iterations, so programmers can follow the paper step-by-step in a more familiar language than 50s mathematical notation. I am no expert in Lisp or mathematics, and intentionally went into this with no knowledge of Lisp beyond the original paper. I did not write it in the most elegant way, but in the simplest way for me to understand. So please don't take this code as a definitive statement on the language. However, this code really helped me to understand the original paper better, and to begin using Lisp with a better grasp of the spirit of the language. I'd welcome any thoughts from those who have more experience with Lisp or comp sci history. https://bit.ly/4dCFj9T April 12, 2026 at 11:01AM

Show HN: Bullseye2D – A Dart library for cross-platform 2D games https://bit.ly/4tHZp7t

Show HN: Bullseye2D – A Dart library for cross-platform 2D games I posted this here about a year ago, but I just pushed a 2.0 release, so I hope you don't mind a second look :) Bullseye2D is a 2D game library for Dart with a very simple API. The new version now supports multi-platform. It compiles to the web via a WebGL2 renderer, or natively to Windows, macOS and Linux through an SDL3 backend (which itself supports Vulkan, DirectX, Metal, and OpenGL renderers). It doesn't depend on Flutter and has very few dependencies (except SDL3). It mostly provides a minimal foundation that you can build your own abstractions on top of. This was also my first time leaning more heavily on AI (Opus) for a large refactor. I tried to review and test everything as good as I could, but honestly for the restructuring parts where I had the AI produce rather big chunks of code, I found reviewing and testing quite exhausting, and I still have a slightly queasy feeling about it. So this is also quite an experiment for me how good I'm able to utilise AI :) https://bit.ly/4tBTHnn https://bit.ly/4ciUyCn April 12, 2026 at 09:39AM

Show HN: macpak (Homebrew Wrapper for macOS) https://bit.ly/4cfhLFG

Show HN: macpak (Homebrew Wrapper for macOS) https://bit.ly/47VUpUk April 12, 2026 at 08:30AM

Show HN: Minimalist template for scientific and academic resumes https://bit.ly/422X4be

Show HN: Minimalist template for scientific and academic resumes https://bit.ly/4sxLSyr April 12, 2026 at 04:46AM

Show HN: HyperFlow – A self-improving agent framework built on LangGraph https://bit.ly/4vhTPdr

Show HN: HyperFlow – A self-improving agent framework built on LangGraph Hi HN, I am Umer. I recently built an experimental framework called HyperFlow to explore the idea of self-improving AI agents. Usually, when an agent fails a task, we developers step in to manually tweak the prompt or adjust the code logic. I wanted to see if an agent could automate its own improvement loop. Built on LangChain and LangGraph, HyperFlow uses two agents: - A TaskAgent that solves the domain problem. - A MetaAgent that acts as the improver. The MetaAgent looks at the TaskAgent's evaluation logs, rewrites the underlying Python code, tools, and prompt files, and then tests the new version in an isolated sandbox (like Docker). Over several generations, it saves the versions that achieve the highest scores to an archive. It is highly experimental right now, but the architecture is heavily inspired by the recent HyperAgents paper (Meta Research, 2026). I would love to hear your feedback on the architecture, your thoughts on self-referential agents, or answer any questions you might have! Documentation: https://bit.ly/4mll1Eh GitHub: https://bit.ly/3PY51vP April 11, 2026 at 05:01AM

Show HN: Sash – tiny macOS utility to reliably cycle through app windows https://bit.ly/4cicPjc

Show HN: Sash – tiny macOS utility to reliably cycle through app windows macOS's built-in cycle window shortcut (⌘` / ⌘@) has always been flaky for me. Probably not a Show HN, but if it annoyed me this much it might be annoying some others. Only tested on the latest macOS — would appreciate any reports from other versions. https://bit.ly/4eddVPU April 11, 2026 at 12:02AM

Show HN: Unlegacy – document everything, from COBOL to AI generated code https://bit.ly/47RGizj

Show HN: Unlegacy – document everything, from COBOL to AI generated code https://bit.ly/4vskSD6 April 10, 2026 at 05:55PM

Show HN: Run GUIs as Scripts https://bit.ly/48G4WTN

Show HN: SmolVM – open-source sandbox for coding and computer-use agents https://bit.ly/4tD1tNQ

Show HN: SmolVM – open-source sandbox for coding and computer-use agents SmolVM is an open-source local sandbox for AI agents on macOS and Linux. I started building it because agent workflows need more than isolated code execution. They need a reusable environment: write files in one step, come back later, snapshot state, pause/resume, and increasingly interact with browsers or full desktop environments. Right now SmolVM is a Python SDK and CLI focused on local developer experience. Current features include: - local sandbox environments - macOS and Linux support - snapshotting - pause/resume - persistent environments across turns Install: ``` curl -sSL https://bit.ly/4edpkzh | bash smolvm ``` I’d love feedback from people building coding agents or computer-use agents. Interested in what feels missing, what feels clunky, and what you’d expect from a sandbox like this. https://bit.ly/4ckmAxC April 10, 2026 at 01:01AM

Show HN: Rust based eBook library for Python, with MIT license https://bit.ly/4mo24AT

Show HN: Rust based eBook library for Python, with MIT license https://bit.ly/4czpdg6 April 9, 2026 at 11:03PM

Show HN: I built Dirac, Hash Anchored AST native coding agent, costs -64.8 pct https://bit.ly/4cuJeo9

Show HN: I built Dirac, Hash Anchored AST native coding agent, costs -64.8 pct Fully open source, a hard fork of cline. Full evals on the github page that compares 7 agents (Cline, Kilo, Ohmypi, Opencode, Pimono, Roo, Dirac) on 8 medium complexity tasks. Each task, each diff and correctness + cost info on the github Dirac is 64.8% cheaper than the average of the other 6. https://bit.ly/4t0sefg April 9, 2026 at 01:06PM

Show HN: Homebutler – I manage my homelab from chat. AI never gets raw shell https://bit.ly/4c9xtlK

Show HN: Homebutler – I manage my homelab from chat. AI never gets raw shell https://bit.ly/4c5Wvlz April 9, 2026 at 01:09PM

Show HN: CSS Studio. Design by hand, code by agent https://bit.ly/48qpGPl

Show HN: CSS Studio. Design by hand, code by agent Hi HN! I've just released CSS Studio, a design tool that lives on your site, runs on your browser, sends updates to your existing AI agent, which edits any codebase. You can actually play around with the latest version directly on the site. Technically, the way this works is you view your site in dev mode and start editing it. In your agent, you can run /studio which then polls (or uses Claude Channels) an MCP server. Changes are streamed as JSON via the MCP, along with some viewport and URL information, and the skill has some instructions on how best to implement them. It contains a lot of the tools you'd expect from a visual editing tool, like text editing, styles and an animation timeline editor. https://bit.ly/4t4hwoe April 9, 2026 at 12:23PM