Show HN: Making Claude Code sessions link-shareable https://bit.ly/4qVwACZ

Show HN: Making Claude Code sessions link-shareable Hey HN! My name is Omkar Kovvali and I've been wanting to share my CC sessions with friends / save + access them easily,so I decided to make an MCP server to do so! /share -> Get a link /import -> resume a conversation in your Claude Code All shared sessions are automatically sanitized, removing api keys, tokens, and secrets. Give it a try following the Github/npm instructions linked below - would love feedback! https://bit.ly/4k44IKZ https://bit.ly/3NhPNR3 January 17, 2026 at 03:50AM

Show HN: Commander AI – Mac UI for Claude Code https://bit.ly/4qZCPpv

Show HN: Commander AI – Mac UI for Claude Code Hi HN, I built Commander, a UI for running multiple AI coding agents in parallel without living in terminal hell. As coding agents got better, I started trusting them with real work: features, end-to-end, refactors, tests. Naturally, I began running 1–3 at once. That’s when the CLI stopped scaling — too many terminals, lost context, scattered diffs. Commander fixes that. https://bit.ly/4qsi5H6 January 17, 2026 at 01:08AM

Show HN: Reversing YouTube’s “Most Replayed” Graph https://bit.ly/3NLBu7c

Show HN: Reversing YouTube’s “Most Replayed” Graph Hi HN, I recently noticed a recurring visual artifact in the "Most Replayed" heatmap on the YouTube player. The highest peaks were always surrounded by two dips. I got curious about why they were there, so I decided to reverse engineer the feature to find out. This post documents the deep dive. It starts with a system design recreation, reverse engineering the rendering code, and ends with the mathematics. This is also my first attempt at writing an interactive article. I would love to hear your thoughts on the investigation and the format. https://bit.ly/4qlpNm9 January 16, 2026 at 03:06AM

Show HN: Gambit, an open-source agent harness for building reliable AI agents https://bit.ly/4qVoWsg

Show HN: Gambit, an open-source agent harness for building reliable AI agents Hey HN! Wanted to show our open source agent harness called Gambit. If you’re not familiar, agent harnesses are sort of like an operating system for an agent... they handle tool calling, planning, context window management, and don’t require as much developer orchestration. Normally you might see an agent orchestration framework pipeline like: compute -> compute -> compute -> LLM -> compute -> compute -> LLM we invert this so with an agent harness, it’s more like: LLM -> LLM -> LLM -> compute -> LLM -> LLM -> compute -> LLM Essentially you describe each agent in either a self contained markdown file, or as a typescript program. Your root agent can bring in other agents as needed, and we create a typesafe way for you to define the interfaces between those agents. We call these decks. Agents can call agents, and each agent can be designed with whatever model params make sense for your task. Additionally, each step of the chain gets automatic evals, we call graders. A grader is another deck type… but it’s designed to evaluate and score conversations (or individual conversation turns). We also have test agents you can define on a deck-by-deck basis, that are designed to mimic scenarios your agent would face and generate synthetic data for either humans or graders to grade. Prior to Gambit, we had built an LLM based video editor, and we weren’t happy with the results, which is what brought us down this path of improving inference time LLM quality. We know it’s missing some obvious parts, but we wanted to get this out there to see how it could help people or start conversations. We’re really happy with how it’s working with some of our early design partners, and we think it’s a way to implement a lot of interesting applications: - Truly open source agents and assistants, where logic, code, and prompts can be easily shared with the community. - Rubric based grading to guarantee you (for instance) don’t leak PII accidentally - Spin up a usable bot in minutes and have Codex or Claude Code use our command line runner / graders to build a first version that is pretty good w/ very little human intervention. We’ll be around if ya’ll have any questions or thoughts. Thanks for checking us out! Walkthrough video: https://youtu.be/J_hQ2L_yy60 https://bit.ly/4sH6hST January 16, 2026 at 01:13AM

Show HN: Control what Claude can access using cloud-based decision table UIs https://bit.ly/4qwXTE8

Show HN: Control what Claude can access using cloud-based decision table UIs We’ve been building visual rule engines (clear interfaces + API endpoints that help map input data to a large number of outcomes) for a while and had the fun idea lately to see what happens when we use our decision table UI with Claude’s PreToolUse hook. The result is a surprisingly useful policy/gating layer– these tables let your team: - Write multi-factor, exception-friendly policies (e.g. deny rm -rf / when --force; allow cleanup only in node_modules; ask on network calls like curl/wget; block kubectl delete or SQL DROP, each with a clear reason) - Roll out policy changes instantly (mid-run, flip a risky operation from allow → ask; the next attempt across devs and agents is gated immediately– no git pull, agent restart, or coordination) - Adopt lightweight governance that survives churn (MCP/skills/etc): just add columns/rules as new tools and metadata show up - Get a quick central utility to understand which tools are being used, which tools get blocked most often, and why https://bit.ly/45fepjl January 15, 2026 at 07:21PM

Show HN: Visibility and Controls for Browser Agents https://bit.ly/49kG8BG

Show HN: Visibility and Controls for Browser Agents Hey HN! I’m Ashwin, co-founder of ContextFort ( https://bit.ly/4jMQnm0 ). We provide visibility and controls for AI browser agents like Claude in Chrome through an open-source browser extension. Browser agents are AI copilots that can autonomously navigate and take actions in your browser. They show up as standalone browsers (Comet, Atlas) or Chrome extensions (Claude). They’re especially useful in sites where search/API connectors don’t work well, like searching through Google Groups threads for a bug fix or pulling invoices from BILL.com. Anthropic released Claude CoWork yesterday, and in their launch video, they showcased their browser-use chromium extension: https://www.youtube.com/watch?v=UAmKyyZ-b9E But enterprise adoption is slow because of indirect prompt injection risks, about which Simon Willison has written in great detail in his blogs: https://bit.ly/3LDV7gR... . And before security teams can decide on guardrails, they need to know how employees are using browser agents to understand where the risks are. So, we reverse-engineered how the Claude in Chrome extension works and built a visibility layer that tracks agent sessions end-to-end. It detects when an AI agent takes control of the browser and records which pages it visited during a session and what it does on each page (what was clicked and where text was input). On top of that, we’ve also added simple controls for security teams to act on based on what the visibility layer captures: (1) Block specific actions on specific pages (e.g., prevent the agent from clicking “Submit” on email) (2) Block risky cross-site flows in a single session (e.g., block navigation to Atlassian after interacting with StackOverflow), or apply a stricter policy and block bringing any external context to Atlassian entirely. We demo all the above features here in this 2-minute YouTube video: https://www.youtube.com/watch?v=1YtEGVZKMeo You can try our browser extension here: https://bit.ly/4bFL19M Thrilled to share this with you and hear your comments! https://bit.ly/4jMQnm0 January 14, 2026 at 10:22AM

Show HN: IMSAI/Altair inspired microcomputer with web emulator https://bit.ly/3Nn6tXd

Show HN: IMSAI/Altair inspired microcomputer with web emulator I designed and built a physical replica of a 1970s-style front panel microcomputer with 25+ toggle switches, 16 LEDs, and an LCD display. The brain is a Raspberry Pi Pico running an Intel 8080 CPU emulator. The main twist: I decided to see how far I could get using Claude Code for the firmware. That and the web emulator were written almost entirely using Claude Code (Opus 4.5). I've kept the full prompt history here: https://bit.ly/3NjenRu.... It was able to create the emulator in just a few prompts! It really surprised me that it was able to make a WebAssembly version from the same code (compiled with emscripten) and get the physical layout of the panel from a given photo. It also created some simple working examples using 8086 instructions! Repository: https://bit.ly/3NdJzBF https://bit.ly/3NhAOqd January 15, 2026 at 02:57AM

Show HN: Commosta – marketplace to share computing resources https://bit.ly/4bx3q8K

Show HN: Commosta – marketplace to share computing resources https://bit.ly/49nLOLl January 15, 2026 at 03:00AM

Show HN: Chklst – A Minimalist Checklist https://bit.ly/4qqmudE

Show HN: Chklst – A Minimalist Checklist Welp... I finally shipped. This is my first real project. I wanted a checklist app the way I wanted it so I built chklst. What’s different? Simple, drag & drop reordering, keyboard shortcuts, color labels. There’s a live demo on the landing page so you can try it without signing up. Free accounts can create 1 list. Premium is $5/month for up to 25 lists + shareable lists. What do you think? I built it with Next.js 16 + Turso/libSQL + Drizzle + Better Auth + Stripe. https://bit.ly/4qkOhvL Would love feedback on onboarding, UX, and pricing. Thanks everyone! https://bit.ly/4qkOhvL January 15, 2026 at 02:48AM

Show HN: Microwave – Native iOS app for videos on ATproto https://bit.ly/3LKyxTR

Show HN: Microwave – Native iOS app for videos on ATproto Hi HN — I built Microwave, a native iOS app for browsing and posting short-form videos, similar to TikTok, but implemented as a pure client on top of Bluesky / AT Protocol. There’s no custom backend: the app reads from and publishes to existing ATproto infrastructure. The goal was to explore whether a TikTok-like experience can exist as a thin client over an open social protocol, rather than a vertically integrated platform. Things I’d especially love feedback on: - Whether this kind of UX makes sense on top of ATproto - Client-only tradeoffs (ranking, discovery, moderation) - Protocol limitations I may be missing - Any architectural red flags TestFlight: https://apple.co/4aXJnAj https://apple.co/4aXJnAj January 13, 2026 at 06:14PM

Show HN: Vibe scrape with AI Web Agents, prompt => get data [video] https://bit.ly/4qem2Ps

Show HN: Vibe scrape with AI Web Agents, prompt => get data [video] Most of us have a list of URLs we need data from (government listings, local business info, pdf directories). Usually, that means hiring a freelancer or paying for an expensive, rigid SaaS. We built an AI Web Agent platform, rtrvr.ai to make "Vibe Scraping" a thing. How it works: 1. Upload a Google Sheet with your URLs. 2. Prompt: "Find the email, phone number, and their top 3 services." 3. Watch the AI agents open 50+ browsers at once and fill your sheet in real-time. It’s powered by a multi-agent system that can take actions, upload files, and crawl through paginations. Web Agent technology built from the ground up: End to End Agent: we built a resilient agentic harness with 20+ specialized sub-agents that transforms a single prompt into a complete end-to-end workflow. Turn any prompt into an end to end workflow, and on any site changes the agent adapts. Dom Intelligence: we perfected a DOM-only web agent approach that represents any webpage as semantic trees guaranteeing zero hallucinations and leveraging the underlying semantic reasoning capabilities of LLMs. Native Chrome APIs: we built a Chrome Extension to control cloud browsers that runs in the same process as the browser to avoid the bot detection and failure rates of CDP. We further solved the hard problems of interacting with the Shadow DOM and other DOM edge cases. Cost: We engineered the cost down to $10/mo but you can bring your own Gemini key and proxies to use for nearly FREE. Compare that to the $200+/mo some other lead gen tools like Clay charge. Use the free browser extension for login walled sites like LinkedIn locally, or the cloud platform for scale on the public web. We are thinking it can be a great upstream tool to your CRM to generate lists and enrich data. Curious to hear if this would make your lead generation, scraping, or automation easier or is it missing the mark? https://www.youtube.com/watch?v=ggLDvZKuBlU January 14, 2026 at 01:30AM

Show HN: AsciiSketch a free browser-based ASCII art and diagram editor https://bit.ly/3LsKKwu

Show HN: AsciiSketch a free browser-based ASCII art and diagram editor https://bit.ly/4sFPHm8 January 13, 2026 at 11:39PM

Show HN: Modern Philosophy Course https://bit.ly/3LJFioW

Show HN: Modern Philosophy Course Fun module on Thales of Miletus—the beginning of philosophy https://bit.ly/4qUrveo January 13, 2026 at 01:09AM

Show HN: I built a tool to calculate the True Cost of Ownership (TCO) for yachts https://bit.ly/3ZbAaNq

Show HN: I built a tool to calculate the True Cost of Ownership (TCO) for yachts https://bit.ly/4pENiFP January 13, 2026 at 02:11AM

Show HN: Blockchain-Based Equity with Separated Economic and Governance Rights https://bit.ly/3Z7pob1

Show HN: Blockchain-Based Equity with Separated Economic and Governance Rights I've been researching blockchain-based capital markets and developed a framework for tokenized equity with separated economic, dividend, and governance rights. Core idea: Instead of bundling everything into one share, issue three token types: - LOBT: Economic participation, no governance - PST: Automated dividends, no ownership - OT: Full governance control Key challenge: Verifying real-world business operations on-chain without trusted intermediaries. I propose decentralized oracles + ZK proofs, but acknowledge significant unsolved problems. This is research/RFC seeking technical feedback on oracle architecture, regulatory viability, and which verticals this makes sense for. Thoughts? https://bit.ly/4pHIM9v January 13, 2026 at 01:33AM

Show HN: Voice Composer – Browser-based pitch detection to MIDI/strudel/tidal https://bit.ly/4qRTtHC

Show HN: Voice Composer – Browser-based pitch detection to MIDI/strudel/tidal Built this over the weekend to bridge the gap between "can hum a melody" and "can code algorithmic music patterns" (Strudel/TidalCycles) for live coding and live dj'ing. What it does: Real-time pitch detection in browser using multiple algorithms: CREPE (deep learning model via TensorFlow.js) YIN (autocorrelation-based fundamental frequency estimation) FFT with harmonic product spectrum AMDF (average magnitude difference function) Outputs: visual piano roll, MIDI files, Strudel/TidalCycles code All client-side, nothing leaves your machine Why multiple algorithms: Different pitch detection approaches work better for different inputs. CREPE is most accurate but computationally expensive; YIN is fast and works well for clean monophonic input; FFT/HPS handles harmonic-rich sounds; AMDF is lightweight. Let users switch based on their use case. Technical details: React, runs entirely in browser via Web Audio API Canvas-based visualization with real-time waveform rendering The original problem: I wanted to learn live coding but had zero music theory. This makes it trivial to capture melodic ideas and immediately use them in pattern-based music systems. Try it: https://bit.ly/3YCk8vV Works best on desktop. Will work more like a Digital Audio Workbench (DAW). Source: https://bit.ly/3YzlR57 https://bit.ly/3YCk8vV January 12, 2026 at 12:06AM

Show HN: What if AI agents had Zodiac personalities? https://bit.ly/49s3MuM

Show HN: What if AI agents had Zodiac personalities? A fun game for playing moral dilemmas with friends. I gave 12 AI agents zodiac personalities (not that I believe in them) using the same LLM with different personality prompts. https://bit.ly/4bt1ONk January 12, 2026 at 12:49AM

Show HN: Horizon Engine – C++20 3D FPS Game Engine with ECS and Modern Renderer https://bit.ly/49xd8W4

Show HN: Horizon Engine – C++20 3D FPS Game Engine with ECS and Modern Renderer Hi HN, I’m working on an experimental 3D FPS game engine in C++20, aiming to deeply understand engine internals from first principles rather than just using existing frameworks. Currently I'm strictly following LearnOpenGL docs. This project focuses on: Entity-Component-System (ECS) architecture for high performance. OpenGL 4.1 rendering with a PBR pipeline, material system, HDR, SSAO, and shadow mapping. Modular systems: input, physics (Jolt), audio (miniaudio), assets, hot reload. A sample FPS game & debug editor built into the repo. Repo: https://bit.ly/3Ltr5wc This isn’t intended to be a commercial rival to any commercial game engines. it’s a learning and exploration project: understanding why certain engine decisions are made, and how to build low-level engine systems from scratch. I’m especially looking for feedback on: Architecture choices (ECS design, render loop, module separation) Your thoughts on modern C++ engine patterns What you’d build vs stub early in a homemade engine Tips from experienced graphics/engine developers Criticism and suggestions are very welcome — it’s early days and meant to evolve. Thanks for checking it out! https://bit.ly/3Ltr5wc January 10, 2026 at 11:23PM

Show HN: Librario, a book metadata API that aggregates G Books, ISBNDB, and more https://bit.ly/49j7Te0

Show HN: Librario, a book metadata API that aggregates G Books, ISBNDB, and more TLDR: Librario is a book metadata API that aggregates data from Google Books, ISBNDB, and Hardcover into a single response, solving the problem of no single source having complete book information. It's currently pre-alpha, AGPL-licensed, and available to try now[0]. My wife and I have a personal library with around 1,800 books. I started working on a library management tool for us, but I quickly realized I needed a source of data for book information, and none of the solutions available provided all the data I needed. One might provide the series, the other might provide genres, and another might provide a good cover, but none provided everything. So I started working on Librario, a book metadata aggregation API written in Go. It fetches information about books from multiple sources (Google Books, ISBNDB, Hardcover. Working on Goodreads and Anna's Archive next.), merges everything, and saves it all to a PostgreSQL database for future lookups. The idea is that the database gets stronger over time as more books are queried. You can see an example response here[1], or try it yourself: curl -s -H 'Authorization: Bearer librario_ARbmrp1fjBpDywzhvrQcByA4sZ9pn7D5HEk0kmS34eqRcaujyt0enCZ' \ 'https://bit.ly/454p2pd' | jq . This is pre-alpha and runs on a small VPS, so keep that in mind. I never hit the limits in the third-party services, so depending on how this post goes, I’ll or will not find out if the code handles that well. The merger is the heart of the service, and figuring out how to combine conflicting data from different sources was the hardest part. In the end I decided to use field-specific strategies which are quite naive, but work for now. Each extractor has a priority, and results are sorted by that priority before merging. But priority alone isn't enough, so different fields need different treatment. For example: - Titles use a scoring system. I penalize titles containing parentheses or brackets because sources sometimes shove subtitles into the main title field. Overly long titles (80+ chars) also get penalized since they often contain edition information or other metadata that belongs elsewhere. - Covers collect all candidate URLs, then a separate fetcher downloads and scores them by dimensions and quality. The best one gets stored locally and served from the server. For most other fields (publisher, language, page count), I just take the first non-empty value by priority. Simple, but it works. Recently added a caching layer[2] which sped things up nicely. I considered migrating from net/http to fiber at some point[3], but decided against it. Going outside the standard library felt wrong, and the migration didn't provide much in the end. The database layer is being rewritten before v1.0[4]. I'll be honest: the original schema was written by AI, and while I tried to guide it in the right direction with SQLC[5] and good documentation, database design isn't my strong suit and I couldn't confidently vouch for the code. Rather than ship something I don't fully understand, I hired the developers from SourceHut[6] to rewrite it properly. I've got a 5-month-old and we're still adjusting to their schedule, so development is slow. I've mentioned this project in a few HN threads before[7], so I’m pretty happy to finally have something people can try. Code is AGPL and on SourceHut[8]. Feedback and patches[9] are very welcome :) [0]: https://bit.ly/3LtSRsC [1]: https://bit.ly/4btRHI1... [2]: https://bit.ly/4jDyAxp [3]: https://bit.ly/4qgj90J [4]: https://bit.ly/4jyI2lz [5]: https://bit.ly/49ZPPSU [6]: https://bit.ly/4qN49Ho [7]: https://bit.ly/49m1NYM [8]: https://bit.ly/3LtSRsC [9]: https://bit.ly/455EzoN... January 11, 2026 at 12:45AM

Show HN: Symfreq – Analyse symbol frequencies in code (Rust) https://bit.ly/49KkIhr

Show HN: Symfreq – Analyse symbol frequencies in code (Rust) https://bit.ly/3L9Dgyp January 10, 2026 at 11:55PM