Hi HN,Over the last few days I&#x27;ve been building USTPS (UDP Speedy Transmission Protocol Secure), an experimental encrypted transport protocol built on top of UDP.The primary goal of USTPS is low-latency video streaming. A server can take a video source and expose it through a USTPS endpoint, while Linux and Android (Termux) clients receive the stream and expose it locally to applications such as VLC, mpv, and FFmpeg.Although streaming is the main focus, USTPS is not limited to media delivery. It can also be used for other reliable encrypted UDP-based applications, which is why I built USSH on top of it.Some of the main design differences compared to TCP-based transports are:- USTPS is reliable but unordered.
- If packet N is lost, later packets can still be accepted and processed immediately.
- Missing packets are recovered through selective retransmission.
- Ordering is handled by the application layer when needed.This means the transport layer itself does not introduce Head-of-Line Blocking. The tradeoff is that applications which require ordering must implement reordering themselves. I consider this a reasonable tradeoff because it avoids forcing every application to pay the cost of transport-level ordering.For media player compatibility, the default USTPS client creates a local TCP endpoint at 127.0.0.1:1238.The client maintains a small reordering buffer (350 ms by default) to give retransmissions time to arrive before forwarding data to the local TCP stream. This allows existing software such as VLC, mpv, and FFmpeg to work without modification.USTPS currently provides:- Reliable delivery using ACKs and selective retransmissions
- X25519 key exchange
- AEAD encryption (AES-GCM and ChaCha20-Poly1305)
- Optional unordered live output mode
- Stream position metadata
- Multi-client support
- Local TCP compatibility output
- No congestion control (currently intentional)While developing USTPS, I also built USSH, an SSH-like remote shell running entirely over USTPS.USSH uses the same unordered transport underneath, but the client reconstructs and orders terminal data before presenting it to the user. This prevents terminal corruption while still allowing the transport layer itself to remain unordered.USSH includes:- Interactive terminal sessions
- PTY support
- Password authentication
- Host key verification (TOFU)
- End-to-end encrypted communication through USTPSI&#x27;m currently using USSH from my Android phone through Termux to manage my VPS.The project is very young (less than a week old) and is primarily experimental and educational. I&#x27;m interested in feedback from people working on transport protocols, streaming systems, SSH implementations, QUIC, SCTP, and networking software.USTP-Secure:
<a href="https:&#x2F;&#x2F;github.com&#x2F;x1colegal&#x2F;USTP-Secure" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;x1colegal&#x2F;USTP-Secure</a>USSH:
<a href="https:&#x2F;&#x2F;github.com&#x2F;x1colegal&#x2F;USSH" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;x1colegal&#x2F;USSH</a>Internet-Drafts:USTPS Draft:
<a href="https:&#x2F;&#x2F;datatracker.ietf.org&#x2F;doc&#x2F;draft-x1co-ustps&#x2F;" rel="nofollow">https:&#x2F;&#x2F;datatracker.ietf.org&#x2F;doc&#x2F;draft-x1co-ustps&#x2F;</a>USSH Draft:
<a href="https:&#x2F;&#x2F;datatracker.ietf.org&#x2F;doc&#x2F;draft-x1co-ussh&#x2F;" rel="nofollow">https:&#x2F;&#x2F;datatracker.ietf.org&#x2F;doc&#x2F;draft-x1co-ussh&#x2F;</a>Questions, criticism, and suggestions are welcome.

Show HN: Ustps (UDP Speedy Transmission Protocol Secure) and USSH

Show HN: I built a lead list tool to find businesses you can sell to

Anthropic&#x27;s usage analytics dashboard is only available to Team and Enterprise org admins. On a Pro or Max plan all you get is &#x2F;usage and the claude.ai usage page, which show where you stand right now but not where you&#x27;re heading. I looked at various open-source projects but none quite matched what I had in mind: an all-round control panel for Claude Code that&#x27;s also a single binary, with no dependencies and no install steps.The other thing I cared about was forecasting the usage limits. Existing tools do burn-rate projections (ccusage) or percentile heuristics (Claude-Code-Usage-Monitor), which felt too simplistic for what I wanted - I was after a calibrated statistical model with proper credible intervals.I built claumon over the last few months in Go. It runs on Linux, macOS and Windows, with a Homebrew install. It has the usual consumption gauges, cost breakdowns and conversation history, plus two tabs for memory management: after a while I had memories scattered across several projects and wanted to see them in one place and prune the stale ones.In the last few weeks I focused on the forecast model. I started from an empirical-Bayes linear regression with Brownian noise, but ended up with a Gamma process for the path noise: token usage can&#x27;t decrease over time, so Brownian motion, however mathematically convenient, was the wrong choice. The intervals are calibrated against your own recorded history, and there&#x27;s tooling that scores the forecasts out-of-sample, so the coverage is checked rather than assumed.I wrote a formal, versioned spec for the model, and the implementation follows it: <a href="https:&#x2F;&#x2F;github.com&#x2F;fabioconcina&#x2F;claumon&#x2F;blob&#x2F;main&#x2F;internal&#x2F;forecast&#x2F;MODEL.pdf" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;fabioconcina&#x2F;claumon&#x2F;blob&#x2F;main&#x2F;internal&#x2F;f...</a>Everything runs locally - nothing leaves your machine. It&#x27;s open source, MIT. I&#x27;d welcome feedback on the model especially.

Show HN: Claumon – forecasting Claude Code usage limits with a Gamma process

Show HN: Recreate Thinking Machines 276B voice demo with duct tape and 8B model

Show HN: NBSDgames – 21 new, improved, original text games for Unix, DOS, Plan9

Show HN: Kyushu – A self-hostable WASM sandbox for JavaScript workers

Hi HN! We’re Jimmy and Ray. Jimmy is a Thiel Fellow with a Ph. D. from MIT who has worked on programming tools for 15 years; Ray became VP of Sales at a $2B company when he was 19 and has built side-businesses vibe-coding.Last year, we set to answer the question “If AI can write code 100x faster, then why aren’t you shipping 100x faster?” What we learned shocked us — even fairly nontechnical people and solo founders told us they were spending more than half of their development time reading the AI-written code. And much of the rest of the time was spent either de-slop-ping it, or wishing they had done so.As luck turns out, our last two products were a tool that quickly onboards people to large codebases ( <a href="https:&#x2F;&#x2F;x.com&#x2F;0xjimmyk&#x2F;status&#x2F;1873357324229984677" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;0xjimmyk&#x2F;status&#x2F;1873357324229984677</a> ) and trainings that taught deep concepts of code quality to CEOs, YC founders, and engineers at top companies ( mirdin.com ), so we were extremely well-positioned to solve these problems.Command Center is an agentic coding environment focused on quality. With a few keypresses, you can start building 3 features at once and soon have 3 diffs ready, each consisting of 2000 changed lines across 50 files….This is normally the point where you think “Crap, what now?”With Command Center, at this point you simply click “Refactor,” and watch the vibed slop turn into readable robustness. Then you click “Generate Walkthrough,” and then suddenly, to read a 2000 line diff, instead of scrolling up and down trying to make sense of it, you just press the right arrow key 200 times. See something you don’t like? Click on line 37, type “Do this and all other network fetches in the background Cmd+Enter,” and you have a few more agents getting your code into final shape. Click or type “Commit,” “Push,” “Create PR” — you just shipped a high quality, non-slop featureWe’re striving to be the best at every step of the pipeline, but can just try Command Center in pieces wherever you feel your current workflow is weakest. We have users who do all their coding in Zed or the Codex app, and then jump over to Command Center for a walkthrough when it finishes running. There’s even a skill that will pop open a Command Center walkthrough from the environment of your choice. Or you can just keep Command Center running while you do your work elsewhere, and if your AI deletes anything, you have Command Center’s snapshots to the rescue.We launched quietly last year and have been refining since. The quality and usability have kept going up, and Command Center is now ready for a lot more attention.Since our quiet launch, we’ve seen at least a dozen other agentic coding environments appear….approximately all of which have the same feature set focused on the part which is already easy (generating the first version of the code) and with at best a shoddy answer to the hard part (everything that comes after). Command Center’s focus is making the hard parts easy.Here’s what our users have to say:“[The refactorings] give your LLM taste. I’ve never seen an LLM write code this good before.” — Doug Slater, Staff Engineer, Climavision“With Command Center walkthroughs, I can get through a 400-line diff in less than half the time.” — Prateek Kumar, Platfor Engineer, Sumo LogicThis product is not for everyone. If you’re someone who preaches “the prompt is the source, the code is the compiler output,” then you probably won’t enjoy Command Center.But if you want to uphold traditional engineering discipline while also shipping 20 PRs a day, then this is the environment for you.

Show HN: Command Center, the AI coding env for people who care about quality

I built Manob because I kept running into the same frustration with every major social media platform. A feed I couldn&#x27;t control, content that I couldn&#x27;t trust, and also a sense that I (my user data) am the product, not the user.I talked with people about these thoughts and concerns, and added my personal observation. I built this instead:- Chronological feed only. No ranking, no algorithmic shuffling. You follow people, you see all posts from all users, or choose to see posts from friends, pages you follow, and groups you are part of.- Built-in fact-checking and bias detection across text, images, and video. With Human-in-the-loop &amp; AI combined in the process, AI detects, analyzes, and moderates posts, and every contested moderation decision is reviewed by a human against a published set of principles (not just personal judgment only).- Per chat AES-256 encryption. We designed a way that currently, if a chat is attacked and compromised, it doesn&#x27;t have any effect on other chats or the platform in any way - this is constantly being improved, and security is my top priority.- No ads currently. Your data is never sold or shared (minor data is stored, all in encrypted strings)- Child safety filtering is built into the content layer
- Pseudonymous mode for speaking about sensitive topics
- A built-in news feedThe moderation system is designed to evolve; it is more like a constitution than a rulebook. The principles are fixed but can be amended as the platform grows and severe cases emerge. The goal is to detect as accurately as possible, systematically, over claims of neutrality and move on.I&#x27;m still working on figuring out monetization. I&#x27;m thinking of contextual ads that work based on the viewing page&#x27;s contents, and not on your behavioral profile. Additionally, other features like the job board and commercial tools are also an option. None of this is live at the moment, and tbh, I&#x27;m still figuring it out.The platform is currently LIVE with a small early community of active users. I&#x27;m building this solo.I&#x27;m happy to answer your questions&#x2F;feedback&#x2F;suggestions...www.manob.bd

Show HN: Manob: A social media plaform without algorithm, ads, or data-tracking

Show HN: Dont lose your friends, use a Kadoodle to plan your next event

<a href="https:&#x2F;&#x2F;github.com&#x2F;CzaxStudio&#x2F;proton" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;CzaxStudio&#x2F;proton</a> (GitHub)

Show HN: Proton – A easy CGO-free immediate-mode GUI framework for Go

nightwatch is a local-first, read-only layer on top of your monitoring. it groups alert storm into incidents, flags noisy checks and has an agent that can investigate for you live systems. You can e.g. jump from the incident into the agent directly.the reason for this weekend project is that we had a kubernetes upgrade that went wrong, and at some point a rollback wasn&#x27;t possible anymore, so it had to be fixed live during the night while several problems came together. We run a lot of different systems, on-prem and several Kubernetes clusters, and in a situation like that you spend most of the time just figuring out what is actually broken and where.So i thought that it would be pretty cool to have eyes in the dark in each system that can talk to your &quot;brain&quot;.so the idea is to put a baby owl into each environment. Each owl runs where the systems live, keeps that environment&#x27;s credentials local, and only dials outbound to a central brain, so there is no inbound hole into prod. It exposes a set of read-only skills, and the agent uses them to gather evidence and form a root-cause hypothesis, so the on-call engineer starts with a head start instead of from zero.read-only for now, i don&#x27;t trust it near prod yet and honestly neither should you.llocal-first for easy self-hosting and to keep credentials on your side. the clustering and recommendations run fully offline with no llm at all. the agent needs a tool-calling llm, you can point it at a remote one, or self-host one (ollama etc.) if you want to stay fully offline.for non selfhosters: before every remote llm call, nightwatch strips real secrets (unrestorable) and swaps identifiers like ips, hostnames and paths for reversible placeholders, so the model only sees masked data while real values are restored only in the proposed commands and tool callsWould love if you try it in your Systems

Show HN: Nightwatch, The open-source, read-only AI SRE

Hey HN, I built this a side project because I&#x27;m a soccer fan that has been vibing and tokenmaxxing with Claude Code maybe too much. So, the World Cup is here and it was the perfect excuse to build and ship something from 0 to 1. Enter Claudinho, a CLI and MCP that puts World Cup scores on your terminal. No signup, no account, no data collection.The components are:
- status line in Claude Code with live scores rendered always from cache, no polling.
- userPromptSubmit hook so Claude gets score updates mid vibecoding session, only during a live match.
- A standard MCP server and a CLI with options to see groups, standings, matches and market signal info.More details in Github. Let me know what you think, I hope you find it fun and useful!Not affiliated with FIFA or Anthropic.

Show HN: A Claude Code statusline that shows live World Cup scores

Hi HN,I&#x27;m the creator of Mach (<a href="https:&#x2F;&#x2F;github.com&#x2F;octalide&#x2F;mach" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;octalide&#x2F;mach</a> or <a href="https:&#x2F;&#x2F;machlang.org" rel="nofollow">https:&#x2F;&#x2F;machlang.org</a>). Two days ago, we finally achieved full self hosting. I wanted to make a post here to show off the language since this is a big milestone for us.## TL;DR about the language for those curious:- There are no external dependencies anywhere in the pipeline. This includes LLVM, libc bindings, or anything of the sort (save for the historical bootstrap compiler, which requires any C compiler and has been phased out completely).- Mach is extremely opinionated and very anti-magic. WYSIWYG is a core principal for the language. There are no hidden behaviors, implicit type conversions, or &quot;automatic features&quot;. Simplicity and stripping away ambiguity are core principals that this language upholds.- Performance currently lags behind C by about a factor of only 4x at the time of writing, almost entirely due to the lack of deep compiler optimizations like autovectorization, which have not been fully implemented yet. Eventually, Mach will be at least on par with C.## Why did I build this?I love low level systems languages like C, Zig, Go, and (sometimes) Rust, but I wanted something that actively discourages &quot;cleverness&quot; in favor of long-term maintainability and overall clarity. Mach is highly opinionated and explicitly demands verbosity in ways that other languages are afraid to. Computers aren&#x27;t magic, and code you write should not pretend they are.
This project initially started out as a learning opportunity for myself, but grew into a fully featured language as time went on. There is still a lot I have to learn, however, and I&#x27;m excited to be able to do so as this project continues to grow into the future.## Why do I (the reader) care?If you like C, you&#x27;ll probably like Mach. Mach takes heavy inspiration from the &quot;vibe&quot; of writing C, but improves on much of the syntax, lacks quite a few footguns, &quot;unhides&quot; a lot of internal mechanisms, and has a FAR better dependency management system.If you want to play around with a language that is fully capable of replacing C, and especially if you would like to contribute to its development, then PLEASE stop by and mess around.## Where should I go to check it out?The github repository has a link to our discord if you&#x27;d like to chat with myself or our few other regular users.
My personal account has all of the tooling that exists as well as a few example repos if you feel inclined to try it out.## Will this project by dead in X months?I&#x27;ve been working on this in the background for over 2 years now. This is a long term project that I plan to maintain into the indefinite future, with or without a userbase.
If you like the language at all, I highly encourage you to get involved in its development because it WILL be sticking around in some capacity forever.I know this was a bit &quot;rambly&quot;, but let me just say that it&#x27;s been a great joy to work on this project and I would love any and ALL opinions and contributions, ESPECIALLY if you hate the language or find a problem that needs fixing.
Let me know what you guys think!

Show HN: Mach – A compiled systems language looking for contributions

Hi HN, I&#x27;m one of the creators of Buildy.More and more people seem to be building personal software, including myself. But I keep re-implementing the same things: authentication, database setup, creating an API&#x2F;MCP server to integrate them into my AI agent.We built Buildy for LLM generated personal apps.How it works: Buildy exposes an API and MCP that the agent can call with an ES module plus an optional UI and CSS. We run the ES module on a workerd isolate with a persistent KV store, then release your UI to a live URL only accessible by you.
Not only that, but your app APIs are exposed securely over both HTTP and MCP so your agent can call them and use the apps you build (log a meal, create a workout plan, update a note, etc.)If your AI chat client supports MCP Apps, we can also render your app inline via an iframe. This works today with ChatGPT and Claude.Here is an app I built to track my nutrition: <a href="https:&#x2F;&#x2F;app.buildy.so&#x2F;app&#x2F;f5da0700-0db7-44ef-9aa2-b9499b484dfd" rel="nofollow">https:&#x2F;&#x2F;app.buildy.so&#x2F;app&#x2F;f5da0700-0db7-44ef-9aa2-b9499b484d...</a> ← You can actually claim this app and remix it with your own agent.To ship a completely new app, drop this prompt into your agent: Read <a href="https:&#x2F;&#x2F;buildy.so&#x2F;start.md" rel="nofollow">https:&#x2F;&#x2F;buildy.so&#x2F;start.md</a> then help me create my first app.Or check out our landing page (<a href="https:&#x2F;&#x2F;buildy.so" rel="nofollow">https:&#x2F;&#x2F;buildy.so</a>) to use our ChatGPT app or connect it to Claude via MCP.I personally use apps I built every day. I&#x27;d love to hear from other people building and using their own personal apps.Would love feedback from people building and using their own personal apps.

Show HN: Deploy personal apps with your agent via Buildy

Alot of companies (Including the one i work at fulltime) use third party email builders to provide custom email functionality to users. However this is a niche sector and the prices are... insane?So to try and fix this i built Maillune, a embeddable emailbuilder sdk that is alot cheaper with a usable free tier for hobby projects. The entire goal was to make the features transparent and logical. With lower focus on feature paywalls and aiming on a more &quot;Out of the box&quot; approach.This is one of my recent projects ive built in parallel with my fulltime job. All feedback is welcome, good or bad!

Show HN: Maillune – Embeddable drag-and-drop email editor as a single component

Built this github style git diff TUI, hope others find it useful. Very focused in scope compared to other existing tools. Includes a stats view showing contributors rank, AI agent usage and other useful stuff.

Show HN: Diffcat – a TUI for delightful Git diffs

Show HN: Iris – pure-Swift ARM64 disassembler with a semantic layer

It started after reading Stephen King&#x27;s &quot;On Writing&quot; where he likened the art of writing as the unearthing of an archeological site after you stumbled upon a unique bone of a story. His advice was to choose a domain you are deeply intimate with. For me, I&#x27;ve been a struggling startup founder for 15 years—enough material to inspire a novel.A 1,000-word writing exercise turned into a complete 125k-word manuscript over the course of a year.In year 1, I learned the sheer joy of unencumbered creative flow and authentic expression. A similar flow I used to get from coding (and more recently vibe coding). What made it effortless was a mindset that I was writing for the sake of it, not with the intention of publishing.After a year of keeping it close to my chest, I decided to show it to a few close friends. They liked some of it, destroyed some of it. Some ultimately encouraged me to publish it.In year 2, I learned about the chasm between writing for myself and writing for an audience. Nerdy stuff I thought were clever completely flew over my readers&#x27; heads. So I studied a dozen textbooks on literature, prose, poetry, voice, grammar, and completely rewrote the manuscript twice over, this time with the audience in mind. There is a lot more finesse to writing than I originally appreciated.In year 3, I felt ready to pitch literary agents. The reason wasn&#x27;t to make a career out of writing, but to learn from professionals. After 100 personalized pitches and 0 offers of representation, I learned that pitching agents was much harder than pitching VCs. Especially for a niche novel like mine; fellow startup founders was too small of a TAM.In year 4, I engaged with a professional author&#x2F;editor (Rob Hart, author of The Warehouse), who gave me essays worth of incredible developmental feedback. Lots of nuanced feedback I couldn&#x27;t get from textbooks. Per his advice, I started back at chapter 1 and refactored the whole manuscript. I distilled it down to the best 88k words.The tinkering never stops; when do you know it&#x27;s done? I realized that I kept on tinkering because it was more comfortable than overcoming the fear of launching. Today, on 06&#x2F;08&#x2F;26, almost 5 years after that Stephen King writing exercise, I&#x27;m ready to say “ship it.”Blockchained is a near-future startup sci-fi thriller that chronicles a struggling startup founder who meets a mysterious investor in Hong Kong. Little does he know that the too-good-to-be-true investor works for the Chinese government.Blockchained was written for the fellow startup founders, engineers, and near-future sci-fi enthusiasts. In other words, HN community, you are my target audienceSample chapters available at <a href="https:&#x2F;&#x2F;www.blockchainednovel.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.blockchainednovel.com&#x2F;</a> — eBook and paperback available today. Hardcover edition coming soon.I suppose we live in an era where it must be qualified that Blockchained was 99.9% lovingly handcrafted. No AI was used to write this novel aside from research, spellcheck, grammar, and the occasional phrasing checks.

Show HN: Startup sci-fi novel that took me 5 years to write

Hey HN, here&#x27;s the repo if you&#x27;d like to try it out: <a href="https:&#x2F;&#x2F;github.com&#x2F;Kaelio&#x2F;ktx" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Kaelio&#x2F;ktx</a>Blog post here: <a href="https:&#x2F;&#x2F;www.kaelio.com&#x2F;blog&#x2F;open-source-anthropic-internal-data-analytics-engine">https:&#x2F;&#x2F;www.kaelio.com&#x2F;blog&#x2F;open-source-anthropic-internal-d...</a>Would love your feedback.

Show HN: Open-source version of Anthropic's internal analytics engine

Show HN: Heard – offline LoRa mesh that keeps hiking groups together

A process can&#x27;t leak a secret it never had.Shai-hulud, prompt-injection - you name it. They cannot steal what your agent (or an process) don&#x27;t have.I run coding agents (Claude Code, Codex) on my own machines most of the day. Every one of them wants real API keys in env and I was scratching my head for the last few months how to contain it.The usual answer to this is a firewall. I don&#x27;t buy it. A firewall tries to contain a secret the process is still holding, and the rules are painful to maintain.AVP gives the agent a placeholder and injects the real value at the last moment, on the wire:
```
# the agent&#x27;s env holds only a placeholder
STRIPE_API_KEY=avp-placeholder
# agent sends: Authorization: Bearer avp-placeholder
# AVP forwards upstream: Authorization: Bearer sk_live_...real...
```Keep your passwords in your vault where they belong. AVP initially relies on Bitwarden as a secret manager. It&#x27;s MIT licensed.Appreciate any feedback.

Show HN: AVP – an agent can't leak a secret it never had

Show HN: Pacman AI – Generated with Claude Fable 5

Show HN: Jailbreak this model to get 3B tokens

We’ve spent the last couple of months building Stillwind Search, a search engine for electronic components that helps users find parts that fit even the most complex set of specifications.After talking to the people that actually build PCBs we found out that finding the exact part you are looking for, is consuming enormous amounts of times, is very tedious and then often doesn’t yield the best results. So we tried to cut down this search time by just requiring a (broad) description of the specifications and we find the correct part in minutes, not hours.This is possible through our own database of parts and their properties. We used LLMs to extract every parameter about a part into &gt;1k schemas, collectively covering more than 130k properties. This depth of properties could no longer be visualized, so the database is queried interactively by an AI agent (Sonnet 4.6) to find the needle in the haystack of parts. Before results are shown, we use another model to verify the data (that’s why it might take a moment before the first results appear).We currently have almost all microcontrollers, sensors, and other advanced ICs on the market, as well as a wide selection of passives and generic parts. We are working on adding more parts and are more than happy to take suggestions.I know that folks on HN like technical details on how this works, so let me give a short overview:
Frontend: SvelteKit + Cloudflare Workers + Hyperdrive
Backend: PostgreSQL 18 (with io_uring) database, with extensions on NVMe drives hosted on a beefy server.We appreciate all feedback and are happy to answer any questions :)Btw: We are already working on a way that you can search combinations of parts, finding the optimal combination of parts.

Show HN: Stillwind – High Resolution Electronic Component Search

I was not getting good cache utilization when including dynamic context in agent threads. After a lot of experimentation, I found a good pattern that minimizes how often long lived conversation history gets modified while still supporting dynamic context. It has flexible hooks for doing things like truncating or summarizing tool outputs when transitioning messages to the long term history. And I&#x27;m seeing &gt;&gt;90% of tokens hitting the cache for my agents despite including a lot of dynamic user context.There are a wide range of agent prompting strategies so I&#x27;d love to hear where this library works well and where there are patterns that don&#x27;t fit well into the current API!

Show HN: Llmbuffer – Python library for cache-optimized LLM conversation history

I posted a version of this over a year ago but decided to rebuild it recently.Bored Spreadsheet is a collection of quick and easy games that look like a spreadsheet from a distance. I have tightened the app to be a collection of 6 games: Minesweeper, 2048, solitaire, sudoku, a market trading game and a daily reconciliation puzzle where the player must find bad data in a fake table.The games are free to play but sign up is required to submit your scores to the leaderboard. As was the original intention over a year ago, I hope this proves useful to those office workers who have a lot of downtime in between tasks or meetings yet don’t have the freedom to open Youtube or Cyberpunk 2077 on their work computers. Ironically my work network has blocked the website as it “contains non-business-related services” – I hope you have better luck than me!

Show HN: Quick games disguised as boring spreadsheets

Hello HN,What is CambiOS?A microkernel OS built in Rust, that boots in QEMU under x86_64, AArch64, and RISC-V - targeting formal verification. Processes are assigned unforgeable cryptographic identity and IPC gates access to only allowed endpoints.What does it want to be? Ambitious. Cutting away latent security issues, corporate surveillance, centralized identity and data hosting, and OPEN. With the advent of the coding tools, building the things we want is a bit less of a lift. Could it replace Windows? Sure. That&#x27;s where the idea was born.Secure and intuitive, in a nutshell.I&#x27;ve been working on this for a couple of years and coding earnestly for months. Looking for feedback and would LOVE to find collaborators.I saw a hole in the OS landscape and am working to close it - the closest other alternative I could find is Google&#x27;s Fuschia (not sovereign by any stretch.)I&#x27;m Jason, here for questions if they come up.. cheers!More info here: <a href="https:&#x2F;&#x2F;coherentforge.com&#x2F;cambios" rel="nofollow">https:&#x2F;&#x2F;coherentforge.com&#x2F;cambios</a>