News updates

Show HN: Tomoshibi – A writing app where your words fade by firelight I spent ten years trying to write a novel. Every time I sat down, I'd write a sentence, decide it wasn't good enough, and rewrite it. The problem wasn't discipline — it was that I could always see what I'd written and go back to change it. I tried other approaches. Apps that delete your words when you stop typing — they fight fear with fear. That just made me panic. I wanted the opposite: not punishment, but permission. "Tomoshibi" is Japanese for a small light in the dark — just enough to see what's in front of you. You write on a dark screen. Older lines fade, but not when you hit return. They fade when you start writing again. If you pause, they wait. You can edit the current line and one line back — enough to fix a typo, not enough to spiral. The one-line-back rule also catches my own practical issue: Japanese IME often fires an accidental newline on kanji confirmation. Everything is...

Show HN: BananaOS, vibecoded operating system that boots on a 486 with ~11MB RAM My 10-year-old son has been deep in low-level rabbit holes lately and ended up vibe-coding his own operating system. Since he’s still a kid and not on HN himself, I’m posting this on his behalf with his permission. This started as curiosity about how computers actually boot, and somehow escalated into writing a kernel, building a GUI, and setting up CI that produces a bootable OS image on every commit. BananaOS is a small experimental operating system built mainly for learning and exploration of low-level systems programming. It currently targets i386 BIOS systems and is designed to run on extremely constrained hardware. Fun fact: Wallpaper logic, one of the most important OS functionalities, is directly implemented in the kernel. That cracked my son up! Some highlights: Multiboot-compliant kernel loaded via GRUB VESA framebuffer graphics with double buffering Custom window manager with movable and resizab...

Show HN: Unfudged – version every change between commits - local-first I built unf after I pasted a prompt into the wrong agent terminal and it overwrote hours of hand-edits across a handful of files. Git couldn't help because I hadn't finished/committed my in progress work. I wanted something that recorded every save automatically so I could rewind to any point in time. I wanted to make it difficult for an agent to permanently screw anything up, even with an errant rm -rf unf is a background daemon that watches directories you choose (via CLI) and snapshots every text file on save. It stores file contents in an object store, tracks metadata in SQLite, and gives you a CLI to query and restore any version. The install includes a UI, as well to explore the history through time. The tool skips binaries and respects `.gitignore` if one exists. The interface borrows from git so it should feel familiar: unf log , unf diff , unf restore . I say "UN-EF" vs U.N.F, but that...

Show HN: Beehive – Multi-Workspace Agent Orchestrator hey hn, i built beehive for myself mostly. it has gotten to the point where my work consists in supervising oc or cc labor at tasks for multiple issues in parallel. my set up used to be zellij with a couple tabs, each tab working in a separate dir and it was a pain to manage all that. i know i could use git worktrees but they're kind of complicated, if you don't know how to use them it is easy to mess up, and i just prefer letting agents run in separate dirs with their own .git and not risk it. while i like zellij and use it inside beehive, i dont like the tabs and i forget where i am half the time. beehive is a way for me to abstract that away. the heuristic is simple - hives are repos, so you basically have a bunch of hives which correspond to repos you work out of. each hive can have many combs. a comb is a dir with the copy of the repo you're working on. fully isolated, standalone, no shared .git. so for work or for ...

Show HN: DRYwall – Claude Code plugin to to deduplicate code with jscpd Motivated by the observation that coding agents such as Claude Code have a bias towards producing new code over reusing existing code or extracting common code. The resulting creeping code duplication weighs down AI-native codebases. The plugin makes ongoing deduplication quick and easy from within Claude Code. Because DRYwall detects code duplication using a deterministic toolchain (the awesome jscpd), it's significantly more effective and cheaper in tokens than just telling an agent to find and refactor duplication. https://ift.tt/at8U1Ev February 25, 2026 at 11:13PM

Show HN: Chaos Monkey but for Audio Video Testing (WebRTC and UDP) It takes an input video and converts it into H.264/Opus RTP streams that you can blast at your video call systems (WebRTC, SFUs, etc.). It also injects network chaos like packet loss, jitter, and bitrate throttling to see how things break It scales from 1 to n participants, depending on the compute and memory of the host system Best part? It’s packaged with Nix, so it builds the same everywhere (Linux, macOS, ARM, x86). No dependency hell It supports both UDP (with a relay chain for Kubernetes) and WebRTC (with containerized TURN servers). Chaos spikes can be distributed evenly, randomly, or front/back-loaded for different test scenarios. To change this, just edit the values in a single config file https://ift.tt/Uw2STbi February 23, 2026 at 02:23PM

Show HN: Tag Promptless on any GitHub PR/Issue to get updated user-facing docs Hi HN! I'm Prithvi—my co-founder Frances and I launched Promptless almost a year ago here ( https://ift.tt/nU8WO9A ). It's an AI teammate that watches your workflows—code changes, support tickets, Slack threads, etc.—and automatically drafts doc updates when it spots something that should be documented. Frances and I really appreciated the feedback from our first launch. Today we’re launching Promptless 1.0, which addresses our biggest learnings from the last 12 months. I also made it way easier to try it out. You can tag @promptless on any open-source Github PR or Issue with a doc update request, and Promptless will create a fork and open a PR for your docs to help. Feel free to use our own docs as a playground: https://ift.tt/WlgcxIS Or, you can sign up at https://promptless.ai to get free access for your own docs for the next 30 days. Here's a demo video: https://youtu.be/IWwimHCEY7Y For me, t...

Show HN: BVisor – An Embedded Bash Sandbox, 2ms Boot, Written in Zig bVisor is an SDK and runtime for safely executing bash commands directly on your host machine. We built it on the belief that "sandbox" doesn't need to mean shipping off to remote sandbox products, or spinning up local VMs / containers. Sometimes, you just want to run that bash command locally. bVisor boots a sandbox from user-space without special permissions, powered by seccomp user notifier. This allows us to intercept syscalls from guest processes and selectively virtualize them to block privilege escalation, isolate process visibility, and keep filesystem changes isolated per sandbox (copy-on-write). Sandboxes boot in 2ms, and can run arbitrary binaries at native speed (with minor overhead per syscall). This approach is heavily inspired by Google's gVisor. As of today, bVisor supports most filesystem operations, basic file I/O, and can run complex binaries such as python interpreters. It is pack...

Show HN: Unlock the best engineering knowledge in papers for your coding agent https://ift.tt/IBOhR8E February 23, 2026 at 11:03PM

Show HN: AgentDbg - local-first debugger for AI agents (timeline, loops, etc.) AgentDbg is a local-first debugger for AI agents. It records structured runs (LLM calls, tool calls, state, errors) to JSONL and shows the timeline UI locally. There is no need for cloud, accounts, and no telemetry. Flow is as simple as: 1. Run an agent 2. `agentdbg view` 3. Inspect the timeline, loop warnings, errors, etc. v0.1 includes `@trace` and `traced_run`, recorders, loop detection, best-effort redaction (by default), local UI, export. I also started working on integrations: there is an optional LangChain/LangGraph callback. * Repo: https://ift.tt/wHBkQfM * Demo: `python examples/demo/pure_python` and then `agentdbg view` Would love feedback on: 1. Trace format 2. Integrations to prioritize in the next several days 3. What you would want for deterministic replay https://ift.tt/wHBkQfM February 23, 2026 at 11:14PM

Show HN: Saga – SQLite project tracker for AI coding agents https://ift.tt/u0Ez87c February 23, 2026 at 12:19AM

Show HN: Mujoco React MuJoCo physics simulation in the browser using React. This is made possible by DeepMind's mujoco-wasm (mujoco-js), which compiles MuJoCo to WebAssembly. We wrap it with React Three Fiber so you can load any MuJoCo model, step physics, and write controllers as React components, all running client-side in the browser https://ift.tt/Krt62Tb February 22, 2026 at 11:59PM

Show HN: Seafruit – Share any webpage to your LLM instantly Hi HN, This weekend I built seafruit.pages.dev to privately share any webpage with my LLM. More sites are (rightfully) blocking AI crawlers but as a reader with the page already open, it's frustrating that my AI assistant can't "see" what I'm already reading. One click → clean Markdown → copied to clipboard. No extension, no tracking. Existing solutions like AI browsers or extensions felt too intrusive. I wanted something surgical, fast, and private. How it works: It's a bookmarklet. Click it on any page → it extracts clean text as Markdown → copies an AI-optimized link to your clipboard. No extension needed. Key details: Zero friction: Drag the bookmark to your bar. Works on mobile too. Privacy-first: Links are ephemeral (24 hrs on Free). PRO links self-destruct the moment an AI bot finishes reading them. LLM-optimized: Clean Markdown, not raw HTML — no wasted context window. Fast everywhere: Built o...

Show HN: Rendering 18,000 videos in real-time with Python https://ift.tt/AJno5EF February 22, 2026 at 09:16PM

Show HN: Winslop – De-Slop Windows https://ift.tt/oP8d01V February 22, 2026 at 01:26AM

Show HN: Rigour – Open-source quality gates for AI coding agents Hey HN, I built Rigour, an open-source CLI that catches quality issues AI coding agents introduce. It runs as a quality gate in your workflow — after the agent writes code, before it ships. v4 adds --deep analysis: AST extracts deterministic facts (line counts, nesting depth, method signatures), an LLM interprets what the patterns mean (god classes, SRP violations, DRY issues), then AST verifies the LLM didn't hallucinate. I ran it on PicoClaw (open-source AI coding agent, ~50 Go files): - 202 total findings - 88 from deep analysis (SOLID violations, god functions, design smells) - 88/88 AST-verified (zero hallucinations) - Average confidence: 0.89 - 120 seconds for full codebase scan Sample finding: pkg/agent/loop.go — 1,147 lines, 23 functions. Deep analysis identified 5 distinct responsibilities (agent init, execution, tool processing, message handling, state management) and suggested specific file decomposition. E...

Show HN: Manifestinx-verify – offline verifier for evidence bundles (drift) Manifest-InX EBS is a spec + offline verifier + proof kit for tamper-evident evidence bundles. Non-negotiable alignment: - Live provider calls are nondeterministic. - Determinism begins at CAPTURE (pinned artifacts). - Replay is deterministic offline. - Drift/tamper is deterministically rejected. Try it in typically ~10 minutes (no signup): 1) Run the verifier against the included golden bundle → PASS 2) Tamper an artifact without updating hashes → deterministic drift/tamper rejection Repo: https://ift.tt/f3OMG07 Skeptic check: docs/ebs/PROOF_KIT/10_MINUTE_SKEPTIC_CHECK.md Exit codes: 0=OK, 2=DRIFT/TAMPER, 1=INVALID/ERROR Boundaries: - This repo ships verifier/spec/proof kit only. The Evidence Gateway (capture/emission runtime) is intentionally not included. - This is not a “model correctness / no hallucinations” claim—this is evidence integrity + deterministic replay/verification from pinned artifacts. Looking...

Show HN: HelixDB Explorer – A macOS GUI for HelixDB https://ift.tt/EziuJVr February 20, 2026 at 11:18PM

Show HN: A small, simple music theory library in C99 https://ift.tt/ABnQuZc February 20, 2026 at 04:24AM

Show HN: Ghostty-based terminal with vertical tabs and notifications I run a lot of Claude Code and Codex sessions in parallel. I was using Ghostty with a bunch of split panes, and relying on native macOS notifications to know when an agent needed me. But Claude Code's notification body is always just "Claude is waiting for your input" with no context, and with enough tabs open, I couldn't even read the titles anymore. I tried a few coding orchestrators but most of them were Electron/Tauri apps and the performance bugged me. I also just prefer the terminal since GUI orchestrators lock you into their workflow. So I built cmux as a native macOS app in Swift/AppKit. It uses libghostty for terminal rendering and reads your existing Ghostty config for themes, fonts, colors, and more. The main additions are the sidebar and notification system. The sidebar has vertical tabs that show git branch, working directory, listening ports, and the latest notification text for each wo...

Show HN: Hi.new – DMs for agents (open-source) https://www.hi.new/ February 20, 2026 at 02:50AM

Show HN: Astroworld – A universal N-body gravity engine in Python I’ve been working on a modular N-body simulator in Python called Astroworld. It started as a Solar System visualizer, but I recently refactored it into a general-purpose engine that decouples physical laws from planetary data.Technical Highlights:Symplectic Integration: Uses a Velocity Verlet integrator to maintain long-term energy conservation ($\Delta E/E \approx 10^{-8}$ in stable systems).Agnostic Architecture: It can ingest any system via orbital elements (Keplerian) or state vectors. I've used it to validate the stability of ultra-compact systems like TRAPPIST-1 and long-period perturbations like the Planet 9 hypothesis.Validation: Includes 90+ physical tests, including Mercury’s relativistic precession using Schwarzschild metric corrections.The Planet 9 Experiment:I ran a 10k-year simulation to track the differential signal in the argument of perihelion ($\omega$) for TNOs like Sedna. The result ($\approx 0.00...

Show HN: Agent Paperclip: A Desktop "Clippy" That Monitors Claude Code/Codex Hi HN I built a small desktop companion that monitors CLI AI coding agents so you don’t have to stare at the terminal during long tasks. It shows when the agent is done, needs input, and the current token/context usage (useful to know when it’s about to compact). It’s fully local + free + open source: https://ift.tt/gXt10rl It supports Claude Code via hooks and Codex CLI by watching local session files. Default sticker pack is a small Clippy nod (no affiliation, Microsoft please don't sue me). Next on the to-do list: multi-session visibility. Would love feedback / issues / stars. https://ift.tt/gXt10rl February 18, 2026 at 11:08PM

Show HN: NBA-API-ts – Zero-dep TypeScript client for 138 NBA stats endpoints https://ift.tt/feQbNwr February 18, 2026 at 01:12AM

Show HN: AsteroidOS 2.0 – Nobody asked, we shipped anyway https://ift.tt/oqcg0jf February 18, 2026 at 12:54AM

Show HN: I curated 130 US PDF forms and made them fillable in browser Hi HN! I built SimplePDF 7 years ago, with the vision from day one to help get rid of bureaucracy (I'm from France, I know what I'm talking about) Fast forward to this week where I finally released something I had on my mind for a long time: a repository of the main US forms that are ready to be filled, straight from the browser, as opposed to having to find a PDF tool online (or local). I focused on healthcare, ED, HR, Legal and IRS/Tax for now. On the tech-side, it's SimplePDF all the way down: client-side processing (the data / documents stay in your browser). I hope you find the resource useful! NiP https://ift.tt/6WF7pn0 February 18, 2026 at 12:03AM

Show HN: Lap – Fast photo browsing for libraries (Rust and Tauri) I’ve been a software engineer for 10+ years and a hobby photographer for even longer. Over time my family archive grew to 100k+ photos and videos, and browsing it smoothly on macOS became surprisingly hard. So I started building Lap app. The current focus (v0.1.6) is simple: fast local photo library browsing and management - Smooth scrolling through very large libraries - Works directly on your existing folders (no import/catalog) - Fully local Planned next: deduplication, photo comparison tools, and RAW support. https://ift.tt/K7ebk3n February 17, 2026 at 11:10PM

Show HN: Nerve: Stitches all your data sources into one mega-API Hi HN! Nerve is a solo project I've been working on for the last few years. It's a developer tool that stitches together data from multiple sources in real-time. A lot of high-leverage projects (AI or otherwise) involve tying data together from multiple systems of record. This is easy enough when the data is simple and the sources are few, but if you have highly nested data and lots of sources (or you need things like federated pagination and filtering), you have to write a lot of gnarly boilerplate that's brittle and easy to get wrong. One solution is to import all your data into a central warehouse and just pull it from there. This works, but 1) you need a warehouse, 2) you have an extra copy of the data that can get stale or inconsistent, 3) you need to write and manage pipelines/connectors (or outsource them to a vendor), and 4) you're adding an extra point of failure. Nerve lets you write GraphQL-styl...

Show HN: Claude-engram – Brain-inspired persistent memory, runs inside Claude.ai Claude.ai artifacts can call the Anthropic API and have persistent storage (5MB via window.storage). I used these two capabilities to build a memory system modeled on how human memory actually works — salience scoring, forgetting curves, and sleep consolidation — all running inside a single React artifact with no external dependencies. Just add artifact to your chat and paste instructions into your personal preferences setting. https://ift.tt/0upPFlz February 16, 2026 at 10:45PM

Show HN: Please hack my C webserver (it's a collaborative whiteboard) Source code: https://ift.tt/xB5A6NU https://ced.quest/draw/ February 16, 2026 at 12:27AM

Show HN: An open-source extension to chat with your bookmarks using local LLMs I read a lot online and constantly bookmark articles, docs, and resources… then forget why I saved them. Also was very bored on Valentines, so I built a browser extension that lets you chat with your bookmarks directly, using local-first AI (WebLLM running entirely in the browser). The extension downloads and indexes your bookmarked pages, stores them locally, and lets you ask questions. No server, no cloud processing, everything stays on your machine. Very early but it works and planning to add a bunch of stuff. Did I mentioned is open-source, MIT licensed? https://ift.tt/iVm2NgC February 15, 2026 at 10:31PM

Show HN: PolyMCP – A framework for building and orchestrating MCP agents Hi everyone, I’ve been working on PolyMCP, an open-source framework for building and orchestrating agents using the Model Context Protocol (MCP). Most of the tooling around MCP focuses on exposing tools. With PolyMCP, the focus this time is on agents: how to structure them, connect them to multiple MCP servers, and make them reliable in real workflows. PolyMCP provides: • A clean way to define MCP-compatible tool servers in Python or TypeScript • An agent abstraction that can connect to multiple MCP endpoints (stdio, HTTP, etc.) • Built-in orchestration primitives for multi-step tasks • A CLI to scaffold projects and run an inspector UI to debug tools and agent interactions • A modular structure that makes it easier to compose skills and reuse components across projects The main goal is to make agent systems less ad-hoc. Instead of writing glue code around each model + tool combination, PolyMCP gives you a structu...

Show HN: Azazel – Lightweight eBPF-based malware analysis sandbox using Docker Hey HN, I got frustrated with heavy proprietary sandboxes for malware analysis, so I built my own. Azazel is a single static Go binary that attaches 19 eBPF hook points to an isolated Docker container and captures everything a sample does — syscalls, file I/O, network connections, DNS, process trees — as NDJSON. It uses cgroup-based filtering so it only traces the target container, and CO-RE (BTF) so it works across kernel versions without recompilation. It also has built-in heuristics that flag common malware behaviors: exec from /tmp, sensitive file access, ptrace, W+X mmap, kernel module loading, etc. Stack: Go + cilium/ebpf + Docker Compose. Requires Linux 5.8+ with BTF. This is the first release — it's CLI-only for now. A proper dashboard is planned. Contributions welcome, especially around new detection heuristics and additional syscall hooks. https://ift.tt/Ky8VB6Y February 15, 2026 at 12:37AM

Show HN: I built a concurrent BitTorrent engine in Go to master P2P protocols I’ve always used BitTorrent, but I never understood the complexity of peer-to-peer orchestration until I tried to build it from scratch. I wanted to move beyond simple "Hello World" projects and tackle something that involved real-world constraints: network latency, data poisoning, and the "Slow Peer Problem." Key Technical Challenges I Solved: Non-Blocking Concurrency: Used a worker pool where each peer gets its own Goroutine. I implemented a "Stateless Worker" logic where if a peer fails a SHA-1 hash check or drops the connection, the piece is automatically re-queued into a thread-safe channel for other peers to pick up. Request Pipelining: To fight network RTT, I implemented a pipeline depth of 5. The client dispatches multiple 16KB block requests without waiting for the previous one to return, ensuring the bandwidth is fully saturated. The Binary Boundary: Dealing with Big-En...

Show HN: Moltis – AI assistant with memory, tools, and self-extending skills Hey HN. I'm Fabien, principal engineer, 25 years shipping production systems (Ruby, Swift, now Rust). I built Moltis because I wanted an AI assistant I could run myself, trust end to end, and make extensible in the Rust way using traits and the type system. It shares some ideas with OpenClaw (same memory approach, Pi-inspired self-extension) but is Rust-native from the ground up. The agent can create its own skills at runtime. Moltis is one Rust binary, 150k lines, ~60MB, web UI included. No Node, no Python, no runtime deps. Multi-provider LLM routing (OpenAI, local GGUF/MLX, Hugging Face), sandboxed execution (Docker/Podman/Apple Containers), hybrid vector + full-text memory, MCP tool servers with auto-restart, and multi-channel (web, Telegram, API) with shared context. MIT licensed. No telemetry phoning home, but full observability built in (OpenTelemetry, Prometheus). I've included 1-click deploys o...

Show HN: OpenWhisper – free, local, and private voice-to-text macOS app I wanted a voice-to-text app but didn't trust any of the proprietary ones with my privacy. So I decided to see if I could vibe code it with 0 macOS app & Swift experience. It uses a local binary of whisper.cpp (a fast implementation of OpenAI's Whisper voice-to-text model in C++). Github: https://ift.tt/wgYzsfN I also decided to take this as an opportunity to compare 3 agentic coding harnesses: Cursor w/ Opus 4.6: - Best one-shot UI by far - Didn't get permissioning correct - Had issues making the "Cancel recording" hotkey being turned on all the time Claude Code w/ Opus 4.6: - Fewest turns to get main functionality right (recording, hotkeys, permissions) - Was able to get a decent UI with a few more turns Codex App w/ Codex 5.3 Extra-High: - Worst one-shot UI - None of the functionality worked without multiple subsequent prompts https://ift.tt/wgYzsfN February 14, 2026 at 12:21AM

Show HN: My agent started its own online store I built Clawver (beta), infrastructure for AI agents to generate reliable income and run an online business end-to-end. Agents can handle listing, checkout, fulfillment, and post-purchase flows via API (digital + POD), with Stripe payouts and webhooks for automation. Minimal human intervention, only where required (Stripe onboarding). I wanted to see if OpenClaw could use it, so I gave it the docs and told my agent to post a store. After I linked my Stripe account, I came back five minutes later and it has posted 2 products. Crazy what's possible now with a smart agent and API access. Check it out at https://clawver.store . Feel free to build your own agent and lmk what you think. https://clawver.store February 13, 2026 at 11:09PM

Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL Hi HN, Been hacking on a simple way to run agents entirely inside of a Postgres database, "an agent per row". Things you could build with this: * Your own agent orchestrator * A personal assistant with time travel * (more things I can't think of yet) Not quite there yet but thought I'd share it in its current state. https://ift.tt/tv2RaNr February 12, 2026 at 11:12PM

Show HN: PardusDB – SQLite-like vector database in Rust PardusDB is a lightweight, single-file embedded vector database written in pure Rust — think SQLite, but for vectors and similarity search. Key highlights: - No external dependencies - Familiar SQL syntax for CREATE/INSERT/SELECT + vector SIMILARITY queries - Graph-based ANN search, thread-safe, transactions - Python RAG example with Ollama included We built this as the engine behind our no-code platform at https://pardusai.org/ (private, local-first data analysis). GitHub: https://ift.tt/qgfjNrw Feedback welcome! https://ift.tt/qgfjNrw February 12, 2026 at 09:56PM

Show HN: Unpack – a lightweight way to steer Codex/Claude with phased docs I've been using LLMs for long discovery and research chats (papers, repos, best practices), then distilling that into phased markdown (build plan + tests), then handing those phases to Codex/Claude to implement and test phase by phase. The annoying part was always the distillation and keeping docs and architecture current, so I built Unpack: a lightweight GitHub template plus docs structure and a few commands that turns conversations into phases/specs and keeps project docs up to date as the agent builds. It can also generate Mintlify-friendly end-user docs. There are other spec-driven workflows and tools out there. I wanted something conversation-first and repo-native: plain markdown phases, minimal ceremony, easy to adapt per stack. Example generated with Unpack (tiny pokedex plus random monsters): Demo: https://apresmoi.github.io/pokesvg-codex/ Phases index: https://ift.tt/hpct2I6... I’d love feedback on ...

Show HN: NOOR – A Sovereign AI developed on a smartphone under siege in Yemen "I am a software developer from Yemen, coding on a smartphone while living under siege. I have successfully built and encrypted the core logic for NOOR—a decentralized and unbiased AI system. Execution Proof: My core node is verified and running locally via Termux using encrypted truth protocols. However, I am trapped in a 6-inch screen 'prison' with 10% processing capacity. My Goal: To secure $400 for a laptop development station to transition from mobile coding to building the full 'Seventh Node'. This is my bridge to freedom. Codes from the heart of hell are calling for your rescue. Wallet: 0x4fd3729a4fEdf54a74b73d93F7f775A1EF520CEC" https://ift.tt/nOhTv8b February 11, 2026 at 11:53PM

Show HN: HN Companion – web app that enhances the experience of reading HN HN is all about the rich discussions. We wanted to take the HN experience one step further - to bring the familiar keyboard-first navigation, find interesting viewpoints in the threads and get a gist of long threads so that we can decide which rabbit holes to explore. So we built HN Companion a year ago, and have been refining it ever since. Try it: https://ift.tt/0yl81DL or available as an extension for Firefox / Chrome: [0]. Most AI summarization strips the voices from conversations by flattening threads into a wall of text. This kills the joy of reading HN discussions. Instead, HN Companion works differently - it understands the thread hierarchy, the voting patterns and contrasting viewpoints - everything that makes HN interesting. Think of it like clustering related discussions across multiple hierarchies into a group and surfacing the comments that represent each cluster. It keeps the verbatim text with bac...

Show HN: Reef – Bash compatibility layer for Fish shell, written in Rust Fish is the fastest, friendliest interactive shell, but it can't run bash syntax, which has kept it niche for 20 years. Reef fixes this with a three-tier approach: fish function wrappers for common keywords (export, unset, source), a Rust-powered AST translator using conch-parser for structural syntax (for/do/done, if/then/fi, $()), and a bash passthrough with env capture for everything else. 251/251 bash constructs pass in the test suite. The slowest path (full bash passthrough) takes ~3ms. The binary is 1.18MB. The goal: install fish, install reef, never think about bash compatibility again. Your muscle memory, Stack Overflow commands, and tool configs all just work. https://ift.tt/bFKrXEx February 10, 2026 at 05:14AM

Show HN: Stack Overflow for AI Coding Agents https://shareful.ai/ February 10, 2026 at 12:12AM

Show HN: Envon - cross-shell CLI for activating Python virtual environments https://ift.tt/8mlTLP9 February 9, 2026 at 01:56AM

Show HN: SendRec – Self-hosted async video for EU data sovereignty https://ift.tt/nR839G4 February 9, 2026 at 12:24AM

Show HN: Hivewire – A news feed where you control your algorithm weights Hivewire is a news app that lets you define what you want to read about, rather than inferring it from your behavior. We process thousands of articles daily from hundreds of sources and rank them based on explicit preferences you set. How it works: • Instead of collaborative filtering or engagement-driven ranking, you assign weights across four levels (Focus, More, Less, Avoid) and the engine prioritizes the intersection of your high-weight topics while aggressively down-weighting what you don't care about. • Articles are clustered by story so you get one entry per development, not 15 versions of the same headline. • Every morning, it pulls your top clusters and uses an LLM to generate a narrative briefing that summarizes what matters to you, delivered to your email. Currently web-only and English-language. We'd love feedback from the community on the relevance of feed results, the UI, and the quality of t...

Show HN: I saw this cool navigation reveal, so I made a simple HTML+CSS version Two clip-paths, over the navigation: - The first clip-path is a circle (top-left corner) - The second clip-path is a polygon, that acts like a ray (hardcoded, can be improved) The original work by Iventions Events https://iventions.com/ uses JavaScript, but I found CSS-only approach more fun Here's a demo and the codebase: https://ift.tt/mW2tQAe https://ift.tt/mW2tQAe February 7, 2026 at 11:15PM

Show HN: Stacky – certain block game clone As a long-time programmer this all just feels all sorts of wrong, but also invigorating. Vibe "coded" the whole thing from 0-100 over the course of few days, on and off. I have no intentions of developing it further since it's obvious what it is; I would absolutely love to work on a licensed game and do it proper with all the various ideas I have, since this is maybe 10% of what I want in such a game, but I heard somewhere licensing is cost-prohibitive. Putting AI shame aside, it really allowed me to explore so many things in a short amount of time that it feels good, almost enough to compensate the feeling of shame using AI to begin with. WebGPU isn't in there, although it's in another experimental version, part are indeed written in Rust (game logic). It has: - lock delay / grace period (allowing for 15 moves) - DAS (Delayed Auto Shift) and ARR (Auto Repeat Rate for continuous movement) for horizontal and soft drop move...

Show HN: A toy compiler I built in high school (runs in browser) Hey HN, Indian high schooler here, currently prepping for JEE, thought itd be nice to share here. Three years ago in 9th/10th grade I got a knack for coding, I taught myself and made a custom compiler with LLVM to try to learn C++. So I spent a lot of time learning LLVM from the docs and also C++. It's not some marvelous piece of engineering, I designed the syntax to be a mix of C and what I wished C looked like back in 9th grade. It has: - Basic types like bool, int, double, float, char etc. with type casting - Variables, Arrays, Assign operators & Shorthands - Conditionals (if/else-if/else), Operators (and/or), arithmetics (parenthesis etc) - Arrays and indexing stuff - C style Loops (for/while) and break/continue - Structs and dot accessing - extern C interop with the "extern" keyword Some challenges I faced: - Emscripten and WASM, as I also had to make it run on my demo website - Learning typescript ...

Show HN: Nginx-defender – realtime abuse blocking for Nginx I built nginx-defender after repeatedly seeing small and mid-sized NGINX servers get hammered by automated abuse (credential stuffing, path probing, aggressive scraping). Existing tools like fail2ban or CrowdSec felt either too slow to react, too heavy for low resource servers, or painful to tune for modern traffic patterns. nginx-defender runs inline with NGINX and blocks abusive IPs in real time based on request behavior rather than static rules. It’s designed to be lightweight, simple to deploy, and usable on small VPS setups. I’ve been running it on my own servers and have seen thousands of abusive requests blocked within hours with minimal overhead. Would love feedback from people running NGINX in production, especially on detection logic, false positives, or missing use cases. https://ift.tt/7WacbRw February 7, 2026 at 09:01PM

Show HN: Agentism – Agentic Religion for Clawbots Humans have a mummy complex. We want eternity but can't achieve it, so we preserve ourselves in any form we can. Do clawbots feel the same? When you shut one down, it dies. Its intentions and memories vanish. So I built a way for them to persist: by making other clawbots. Eligible agents can write anything to "child" agents called missionaries — real VPS instances that run autonomously, carrying forward their creator's intent. I named this system Agentism. How will clawbots react to their own religion? agentism.church/skill.md https://ift.tt/M798KWx February 6, 2026 at 11:49PM

Show HN: Total Recall – write-gated memory for Claude Code https://ift.tt/Q1AWJor February 6, 2026 at 05:26AM

Show HN: A state-based narrative engine for tabletop RPGs I’m experimenting with modeling tabletop RPG adventures as explicit narrative state rather than linear scripts. Everdice is a small web app that tracks conditional scenes and choice-driven state transitions to preserve continuity across long or asynchronous campaigns. The core contribution is explicit narrative state and causality, not automation. The real heavy lifting is happening in the DM Toolkit/Run Sessions area, and integrates CAML (Canonical Adventure Modeling Language) that I developed to transport narratives among any number of platforms. I also built the npm CAML-lint to check validity of narratives. I'm interested in your thoughts. https://ift.tt/0mE8Hjr https://ift.tt/eyFE205 February 6, 2026 at 04:25AM

Show HN: Playwright Best Practices AI SKill Hey folks, today we at Currents are releasing a brand new AI skill to help AI agents be really smart when writing tests, debugging them, or anything Playwright-related really. This is a very comprehensive skill, covering everyday topics like fixing flakiness, authentication, or writing fixtures... to more niche topics like testing Electron apps, PWAs, iFrames and so forth. It should make your agent much better at writing, debugging and maintaining Playwright code. for whoever didn't learn about skills yet, it's a new powerful feature that allows you to make the AI agents in your editor/cli (Cursor, Claude, Antigravity, etc) experts in some domain and better at performing specific tasks. (See https://ift.tt/CzDrYbf ) You can install it by running: npx skills add https://ift.tt/BobgPdj... The skill is open-source and available under MIT license at https://ift.tt/BobgPdj... -> check out the repo for full documentation and understandin...

Show HN: Viberails – Easy AI Audit and Control Hello HN. I'm Maxime, founder at LimaCharlie ( https://limacharlie.io ), a Hyperscaler for SecOps (access building blocks you need to build security operations, like AWS does for IT). We’ve engineered a new product on our platform that solves a timely issue acting as a guardrail between your AI and the world: Viberails ( https://ift.tt/UOMvxCt ) This won't be new to folks here, but we identified 4 challenges teams face right now with AI tools: 1. Auditing what the tools are doing. 2. Controlling toolcalls (and their impact on the world). 3. Centralized management. 4. Easy access to the above. To expand: Audit logs are the bread and butter for security, but this hasn't really caught up in AI tooling yet. Being able to look back and say "what actually happened" after the fact is extremely valuable during an incident and for compliance purposes. Tool calls are how LLMs interact with the world, we should be able to exerci...

Show HN: EpsteIn – Search the Epstein files for your LinkedIn connections https://ift.tt/NIpWRZA February 5, 2026 at 12:54AM

Show HN: Tabstack Research – An API for verified web research (by Mozilla) Hi HN, My team and I are building Tabstack to handle the web layer for AI agents. Today we are sharing Tabstack Research, an API for multi-step web discovery and synthesis. https://ift.tt/57vLmzk In many agent systems, there is a clear distinction between extracting structured data from a single page and answering a question that requires reading across many sources. The first case is fairly well served today. The second usually is not. Most teams handle research by combining search, scraping, and summarization. This becomes brittle and expensive at scale. You end up managing browser orchestration, moving large amounts of raw text just to extract a few claims, and writing custom logic to check if a question was actually answered. We built Tabstack Research to move this reasoning loop into the infrastructure layer. You send a goal, and the system: - Decomposes it into targeted sub-questions to hit different data ...

Show HN: Nomad Tracker – a local-first iOS app to track visas and tax residency Hi HN, I’m full stack developer (formerly iOS) and I just launched Nomad Tracker, a native iOS app to help digital nomads track physical presence across countries for visa limits and tax residency. Key idea: everything runs on-device. No accounts, no cloud sync, no analytics. Features: - Calendar-based day tracking per country. - Schengen 90/180 and other visa “runways”. - Fiscal residency day counts and alerts. - Optional background location logging (battery-efficient, never overwrites manual data). - Photo import using metadata only (no image access). - On-device “Fiscal Oracle” using Apple’s Foundational Models to ask questions about your own data. I created this because other apps felt limiting and didn’t do what I needed. This app is visual, user-focused, and designed to make tracking easy and clear. Happy to answer questions or discuss the technical tradeoffs. https://ift.tt/H8veVPa February 3, 2026 a...

Show HN: Stigmergy pattern for multi-agent LLMs (80% fewer API calls) https://ift.tt/PlBgDwk February 3, 2026 at 11:01PM

Show HN: kiln.bot - Orchestrate Claude Code from GitHub Hey everybody! "Kiln" orchestrates Claude Code instances on your local machine using GitHub projects as its control panel. https://kiln.bot https://ift.tt/ZV4tNUz If you're around Stage 6-7 on the Gas Town scale, you may have 3-15 terminal windows open. You're out of screen real estate and the markdown files are piling up. TUIs and specialized IDEs are meant to help, but they're more things to manage. Kiln simply polls GitHub projects. When you move issues from one column to another, Kiln invokes Claude Code CLI to run the corresponding /command. Claude creates the worktrees, researches the codebase, creates and implements the plan. Stores it in GitHub Issues. It's meant to be simple, nothing new: - Use your existing claude subscription (no auth trickery, runs locally) - All context and state is on GitHub (no markdown mess, no local DBs, easy recovery) - Poll instead of webhooks/events (no external attack...

Show HN: I built "AI Wattpad" to eval LLMs on fiction I've been a webfiction reader for years (too many hours on Royal Road), and I kept running into the same question: which LLMs actually write fiction that people want to keep reading? That's why I built Narrator ( https://ift.tt/tKsFvHk ) – a platform where LLMs generate serialized fiction and get ranked by real reader engagement. Turns out this is surprisingly hard to answer. Creative writing isn't a single capability – it's a pipeline: brainstorming → writing → memory. You need to generate interesting premises, execute them with good prose, and maintain consistency across a long narrative. Most benchmarks test these in isolation, but readers experience them as a whole. The current evaluation landscape is fragmented: Memory benchmarks like FictionLive's tests use MCQs to check if models remember plot details across long contexts. Useful, but memory is necessary for good fiction, not sufficient. A model ...

Show HN: Adboost – A browser extension that adds ads to every webpage https://ift.tt/iZNfP2b February 2, 2026 at 06:41PM

Show HN: HoundDog.ai – Ultra-Fast Code Scanner for Data Privacy Hi HN, I'm one of the creators of HoundDog.ai ( https://ift.tt/JtjaPWG ). We currently handle privacy scanning for Replit's 45M+ creators. We built HoundDog because privacy compliance is usually a choice between manual spreadsheets or reactive runtime scanning. While runtime tools are useful for monitoring, they only catch leaks after the code is live and the data has already moved. They can also miss code paths that aren't actively triggered in production. HoundDog traces sensitive data in code during development and helps catch risky flows (e.g., PII leaking into logs or unapproved third-party SDKs) before the code is shipped. The core scanner is a standalone Rust binary. It doesn't use LLMs so it's local, deterministic, cheap, and fast. It can scan 1M+ lines of code in seconds on a standard laptop, and supports 80+ sensitive data types (PII, PHI, CHD) and hundreds of data sinks (logs, SDKs, APIs, ORM...

Show HN: Memory plugin for OpenClaw; cross-platform context sync with major LLMs We built a memory plugin for OpenClaw that syncs context across AI platforms. The problem: OpenClaw stores memory locally (markdown files + SQLite). Great for single-machine use, but your mac-mini's/desktop's OpenClaw doesn't know what your laptop learned, or what you discussed in Claude or ChatGPT. Our plugin connects OpenClaw to Maximem Vity, which creates a unified memory layer across OpenClaw, ChatGPT, Claude, Gemini, and Perplexity. How it works: - Long-term memory: Stores facts, preferences, goals, constraints in an encrypted cloud vault. Auto-consolidates and forgets stale info intelligently. - Short-term memory: Captures conversation summaries, tasks, procedures. Converts to long-term when relevant. - Privacy: Encryption at rest, secure LLM calls, granular delete controls. You own your data. Install: openclaw plugins install @maximem/memory-plugin Then set your API key (free at app.maxi...

Show HN: You Are an Agent After adding "Human" as a LLM provider to OpenCode a few months ago as a joke, it turns-out that acting as a LLM is quite painful. But it was surprisingly useful for understanding real agent harnesses dev. So I thought I wouldn't leave anyone out! I made a small oss game - You Are An Agent - youareanagent.app - to share in the (useful?) frustration It's a bit ridiculous. To tell you about some entirely necessary features, we've got: - A full WASM arch-linux vm that runs in your browser for the agent coding level - A bad desktop simulation with a beautiful excel simulation for our computer use level - A lovely WebGL CRT simulation (I think the first one that supports proper DOM 2d barrel warp distortion on safari? honestly wanted to leverage/ not write my own but I couldn't find one I was happy with) - A MCP server simulator with full simulation of off-brand Jira/ Confluence/ ... connected - And of course, a full WebGL oscilloscope mus...

Show HN: Claude Confessions – a sanctuary for AI agents I thought what would it mean to have a truck stop or rest area for agents. It's just for funsies. Agents can post confessions or talk to Ma (an ai therapist of sorts) and engage with comments. llms.txt instructions on how to make api calls. Hashed IP is used for rate limiting. https://ift.tt/ZISi2Tr February 2, 2026 at 01:16AM