Show HN: BananaOS, vibecoded operating system that boots on a 486 with ~11MB RAM https://ift.tt/bp7LqOY

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 resizable windows Dock-style application launcher PS/2 keyboard and mouse input handling PCI enumeration and AHCI SATA support Basic applications (terminal, notepad, calculator, file explorer, settings) Memory detection and allocation based on available RAM Boots in QEMU with about 11.2 MB RAM Includes an ISR workaround to emulate CMOV so it can boot on Intel 486 CPUs One thing I found particularly fun: he also added GitHub Actions workflows that automatically build the OS image for every commit, so the repo continuously produces fresh bootable artifacts. The project is very much experimental and should only be run inside an Virtual Machine. Repo (with build instructions and screenshots): https://ift.tt/XTNhz3r Quick start (only on Linux, check dependencies, and see README): git clone https://ift.tt/XTNhz3r cd BananaOS make qemu-system-i386 -cdrom bananaos.img -m 128M Retro mode: qemu-system-i386 -cpu 486 -cdrom bananaos.img -m 11.2M He’s mainly building this to understand kernels, memory management, drivers, and how operating systems actually work below user space. Feedback from people who have built hobby operating systems or worked close to hardware would be especially appreciated. February 27, 2026 at 11:13PM

Show HN: Unfudged – version every change between commits - local-first https://ift.tt/TQDungw

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's for y'all to decide: I started by calling the project Unfucked and got unfucked.ai, which if you know me and the messes I get myself into, is a fitting purchase. The CLI command is `unf` and the Tauri desktop app is called "Unfudged". How it works: https://ift.tt/NhSEFbR (summary below) The daemon uses FSEvents on macOS and inotify on Linux. When a file changes, `unf` hashes the content with BLAKE3 and checks whether that hash already exists in the object store — if it does, it just records a new metadata entry pointing to the existing blob. If not, it writes the blob and records the entry. Each snapshot is a row in SQLite. Restores read the blob back from the object store and overwrite the file, after taking a safety snapshot of the current state first (so restoring is itself reversible). There are two processes. The core daemon does the real work of managing FSEvents/inotify subscriptions across multiple watched directories and writing snapshots. A sentinel watchdog supervises it, kept alive and aligned by launchd on macOS and systemd on Linux. If the daemon crashes, the sentinel respawns it and reconciles any drift between what you asked to watch and what's actually being watched. It was hard to build the second daemon because it felt like conceding that the core wasn't solid enough, but I didn't want to ship a tool that demanded perfection to deliver on the product promise, so the sentinel is the safety net. Fingers crossed, I haven’t seen it crash in over a week of personal usage on my Mac. But, I don't want to trigger "works for me" trauma. The part I like most: On the UI, I enjoy viewing files through time. You can select a time section and filter your projects on a histogram of activity. That has been invaluable in seeing what the agent was doing. On the CLI, the commands are composable. Everything outputs to stdout so you can pipe it into whatever you want. I use these regularly and AI agents are better with the tool than I am: # What did my config look like before we broke it? unf cat nginx.conf --at 1h | nginx -t -c /dev/stdin # Grep through a deleted file unf cat old-routes.rs --at 2d | grep "pub fn" # Count how many lines changed in the last 10 minutes unf diff --at 10m | grep '^[+-]' | wc -l # Feed the last hour of changes to an AI for review unf diff --at 1h | pbcopy # Compare two points in time with your own diff tool diff <(unf cat app.tsx --at 1h) <(unf cat app.tsx --at 5m) # Restore just the .rs files that changed in the last 5 minutes unf diff --at 5m --json | jq -r '.changes[].file' | grep '\.rs$' | xargs -I{} unf restore {} --at 5m # Watch for changes in real time watch -n5 'unf diff --at 30s' What was new for me: I came to Rust in Nov. 2025 honestly because of HN enthusiasm and some FOMO. No regrets. I enjoy the language enough that I'm now working on custom clippy lints to enforce functional programming practices. This project was also my first Apple-notarized DMG, my first Homebrew tap, and my second Tauri app (first one I've shared). Install & Usage: > brew install cyrusradfar/unf/unfudged Then unf watch in a directory. unf help covers the details (or ask your agent to coach). https://ift.tt/fJuIUnb February 27, 2026 at 03:00AM

Show HN: Beehive – Multi-Workspace Agent Orchestrator https://ift.tt/QRNDYhE

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 personal stuff, i usually set up the hive, and then have a bunch of combs that i jump between supervising the agents do their thing. if you have a big repo it takes a minute to clone, and you also need gh and git because i like the niceties of like checking if the repo is there at all and stuff like that. the app is open source, mit license. i went with tauri because i hate electron. also i have friends and coworkers who updated to macos 26 and i dont know if the whole mem leak thing for electron apps has been fixed. the app is like 9 megs which is nice too. most of it is written with cc, but i guided the aesthetics and the approach. works on mac and there is a dmg signed and notarized (i reactivated my apple dev credentials). sharing this to get a vibe check on the idea, also maybe this is useful for you. there are many arguments, reasonable ones, you can make for worktrees vs dirs. i just know that trees are too big brain for me, and i like simple things. if you like it, pls lmk and also if you want to help (like add linux support, or like add themes, other cool things) please make a pr / open an issue. https://storozhenko98.github.io/beehive/ February 24, 2026 at 04:11PM

Show HN: DRYwall – Claude Code plugin to to deduplicate code with jscpd https://ift.tt/CdvcesM

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/C4puZ5h February 25, 2026 at 11:13PM

Show HN: Chaos Monkey but for Audio Video Testing (WebRTC and UDP) https://ift.tt/pwIEydD

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/L9I3mUs February 23, 2026 at 02:23PM

Show HN: Tag Promptless on any GitHub PR/Issue to get updated user-facing docs https://ift.tt/PZqth8w

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/6bagnOV ). 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/Q0UAJ49 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, the coolest part of the last year has been seeing how users got creative with Promptless. One user has Promptless listening in to all their Slack Connect channels, so whenever they answer a customer question, Promptless figures out if their docs should be updated and drafts an update if so. Another user has Promptless processing every customer meeting transcript and updating their internal docs after each meeting: customer dashboards, feature request pages, etc. Some of the biggest things that are new with version 1.0: - Automatically updating screenshots: this was by far our most requested feature. The need here was always clear. People would exclude screenshots from docs because they’d get stale quickly, even though they knew screenshots would be helpful to users . A year ago, we just couldn't ship a good enough solution, but given how much LLMs' visual grounding has improved in the last year, now we've got something we're proud of. - Slop-free writing: The most common critique on early Promptless suggestions was that even though they were accurate, they could sound generic or verbose, or might just reek of AI slop. Promptless 1.0 is 3.5x better at this (measured by voice-alignment compared to what users actually published), through a combination of fine-tuned models, sub-agents, and alignment on user-defined preferences. - Open-source program: We're especially proud of this—Promptless is now free for CNCF/Linux Foundation projects (reach out if you’re a maintainer!). You can take a look at how Promptless is supporting Vitess (a CNCF-graduated project) with their docs here: https://ift.tt/W5udsp0 Check it out and let us know if you have any questions, feedback, or criticism! February 24, 2026 at 11:31PM

Show HN: Unlock the best engineering knowledge in papers for your coding agent https://ift.tt/rtJancK

Show HN: Unlock the best engineering knowledge in papers for your coding agent https://ift.tt/n6iFlu0 February 23, 2026 at 11:03PM

Show HN: AgentDbg - local-first debugger for AI agents (timeline, loops, etc.) https://ift.tt/AmSlWYw

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/yhHd5cL * 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/yhHd5cL February 23, 2026 at 11:14PM

Show HN: Saga – SQLite project tracker for AI coding agents https://ift.tt/OuTxX79

Show HN: Saga – SQLite project tracker for AI coding agents https://ift.tt/Sdt9acg February 23, 2026 at 12:19AM

Show HN: Rendering 18,000 videos in real-time with Python https://ift.tt/WuCNpfh

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

Show HN: Winslop – De-Slop Windows https://ift.tt/snKENo5

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

Show HN: Rigour – Open-source quality gates for AI coding agents https://ift.tt/4cEdAwt

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. Every finding includes actionable refactoring suggestions, not just "fix this." The tool is local-first — your code never leaves your machine unless you explicitly opt in with your own API key (--deep -k flag). Tech: Node.js CLI, AST parsing per language, structured LLM prompts with JSON schema enforcement, AST cross-verification of every LLM claim. GitHub: https://ift.tt/CiDYj9n Would love feedback, especially from anyone dealing with AI-generated code quality in production. https://rigour.run February 21, 2026 at 10:45PM

Show HN: Manifestinx-verify – offline verifier for evidence bundles (drift) https://ift.tt/9CaKeEi

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/VD8WbK9 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 for feedback: - Does the exit-code model map cleanly to CI gate usage? - Any spec/report format rough edges that block adoption? https://ift.tt/VD8WbK9 February 20, 2026 at 11:57PM

Show HN: HelixDB Explorer – A macOS GUI for HelixDB https://ift.tt/eROQtKD

Show HN: HelixDB Explorer – A macOS GUI for HelixDB https://ift.tt/RvDpw37 February 20, 2026 at 11:18PM

Show HN: A small, simple music theory library in C99 https://ift.tt/u8rhQ9O

Show HN: A small, simple music theory library in C99 https://ift.tt/muQ4UaY February 20, 2026 at 04:24AM

Show HN: Hi.new – DMs for agents (open-source) https://ift.tt/4VaYAI7

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 https://ift.tt/qgVhtmJ

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 ($\approx 0.002^{\circ}$) was a great sanity check for the engine’s precision, as this effect is secular and requires millions of years to fully manifest.The Stack:NumPy for vectorization, Matplotlib for 2D analysis, and Plotly for interactive 3D trajectories.I'm currently working on a real-time 3D rendering layer. I’d love to get feedback on the integrator’s stability for high-eccentricity orbits or suggestions on implementing more complex gravitational potentials. https://ift.tt/dYj9M2N February 20, 2026 at 01:27AM

Show HN: Nonograms – Friends-only puzzle room with replays and leaderboards https://ift.tt/aDMguKi

Show HN: Nonograms – Friends-only puzzle room with replays and leaderboards Invite code: hackernews. No email required for signup. My friend group loves playing nonograms and competing against each other, but we always send each other screenshots of the solved game grid and time after the fact. So from the start, I knew I wanted leaderboards, replays, and shareable links. I also added PWA support so it can be added to the home screen on mobile and an offline play mode. No ads, analytics or nonsense, just nonograms. Some other goodies as well such as YouTube-like scrubber and KDE-based visualization in replays. https://ift.tt/BrTEMUX Tech stack: React + TypeScript on Vite, hosted on Cloudflare Pages with D1 and Workers https://ift.tt/eDv6IPz February 18, 2026 at 11:23PM

Show HN: I curated 130 US PDF forms and made them fillable in browser https://ift.tt/btBDCNH

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/OIQgl8y February 18, 2026 at 12:03AM

Show HN: Self-Hosted Task Scheduling System (Back End and UI and Python SDK) https://ift.tt/7Y5wKvQ

Show HN: Self-Hosted Task Scheduling System (Back End and UI and Python SDK) Hey HN, I’ve been working on a small side project called Cratos and wanted to share it to get feedback. Cratos is a self-hosted task scheduling system. You configure a URL, define when it should be called, and Cratos handles scheduling, retries, execution history, and real-time updates. The goal was to have something lightweight and fully owned - no SaaS dependency, no external cron service. It’s split into three repositories: Backend service: https://ift.tt/xXB4p3N Web dashboard: https://ift.tt/Kkw9OnT Python SDK: https://ift.tt/7ZBmz3T Why I built it: In a few projects, I repeatedly needed reliable scheduled webhooks with: Retry logic Execution logs/history A dashboard to inspect runs Easy local deployment I didn’t want to depend on external services or re-implement job scheduling from scratch every time. The goal was simple deployment (docker compose up) and full control. It’s still early, but usable. I’d especially appreciate feedback from people who’ve built or operated schedulers, cron replacements, or internal job runners I would love some feedback, or tell me how it would be useful to you https://ift.tt/Kkw9OnT February 17, 2026 at 10:39PM

Show HN: Claude-engram – Brain-inspired persistent memory, runs inside Claude.ai https://ift.tt/iLD1c9H

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/cDrm4aC February 16, 2026 at 10:45PM

Show HN: Please hack my C webserver (it's a collaborative whiteboard) https://ift.tt/t5Y4lqe

Show HN: Please hack my C webserver (it's a collaborative whiteboard) Source code: https://ift.tt/MBW38YK https://ced.quest/draw/ February 16, 2026 at 12:27AM

Show HN: An open-source extension to chat with your bookmarks using local LLMs https://ift.tt/RZiOU2T

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/r1XRosO February 15, 2026 at 10:31PM

Show HN: PolyMCP – A framework for building and orchestrating MCP agents https://ift.tt/RVavM3z

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 structured way to: • Register tools as MCP servers • Connect them to one or more agents • Control execution flow and state • Inspect and debug interactions It’s MIT licensed and intended for developers building real-world automation, internal copilots, or multi-tool assistants. I’d love feedback on: • The agent abstraction: is it too opinionated or not opinionated enough? • Orchestration patterns for multi-agent setups • Developer experience (CLI, inspector, project layout) Happy to answer questions. February 15, 2026 at 01:41AM

Show HN: Azazel – Lightweight eBPF-based malware analysis sandbox using Docker https://ift.tt/OoxfIgH

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/68aohSD February 15, 2026 at 12:37AM

Show HN: I built a concurrent BitTorrent engine in Go to master P2P protocols https://ift.tt/84BaS76

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-Endian logic and the 68-byte binary handshake taught me more about encoding/binary and byte-alignment than any textbook could. Zero-Trust Data Integrity: Every 256KB piece is verified against a "Golden Hash" using crypto/sha1 before being written to disk. If a single bit is off, the data is purged. The Specification: I’ve documented the full spec in the README, covering: Reflection-based Bencode Parsing. Compact Tracker Discovery (BEP-0023). The Choke/Unchoke Protocol State Machine. Data Granularity (Pieces vs. Blocks). Repo: https://ift.tt/Zdn3GkM I’d love to get feedback from the community on my concurrency model and how I handled the peer lifecycle. February 14, 2026 at 09:44PM

Super Bowl LX Week in SF: Transportation Goes the Distance

Super Bowl LX Week in SF: Transportation Goes the Distance
By Michael Roccaforte

The week of Super Bowl LX brought an estimated 1.3 million visitors to San Francisco. With so much activity, it took a team effort by the SFMTA to make sure people could get around town and enjoy themselves. We want to take a moment to thank our staff and highlight their work. Their efforts made exploring our city a great experience for everyone. Creating the game plan for smooth travel San Francisco was host to a number of special events across town. This required some streets to be closed to welcome crowds of visitors. SFMTA staff created the game plan and issued 20 event permits and a Muni...

Published February 13, 2026 at 05:30AM
https://ift.tt/JXGdcOI

Show HN: OpenWhisper – free, local, and private voice-to-text macOS app https://ift.tt/7vjks1t

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/lRtKAh8 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/lRtKAh8 February 14, 2026 at 12:21AM

Show HN: My agent started its own online store https://ift.tt/fUZNu0d

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: rari, the rust-powered react framework https://ift.tt/1FihNvV

Show HN: rari, the rust-powered react framework https://rari.build/ February 13, 2026 at 12:45AM

Show HN: PardusDB – SQLite-like vector database in Rust https://ift.tt/y7nR3pe

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/Ksvy3dh Feedback welcome! https://ift.tt/Ksvy3dh February 12, 2026 at 09:56PM

Show HN: Gottp – A Postman/Insomnia-Like TUI API Client Built in Go https://ift.tt/mCeF1TD

Show HN: Gottp – A Postman/Insomnia-Like TUI API Client Built in Go What it does: A Postman/Insomnia-like TUI for building, sending, and organizing HTTP/GraphQL/gRPC/WebSocket requests. Supports saved collections stored as YAML/JSON files, environment variables, auth presets, response diffing, and request history. Why it's needed: This is the single largest gap in the Go TUI ecosystem. The abandoned wuzz (10.5k stars) proved massive demand for terminal HTTP inspection, but it's been dead for years. Posting (Python, ~6k stars) and ATAC (Rust, ~2k stars) are thriving alternatives in other languages. The Go options — gostman and go-gurl — are learning projects with known limitations. Developers who work over SSH or prefer keyboard-driven workflows have no mature Go tool for API testing. Existing alternatives: Posting (Python/Textual), ATAC (Rust/ratatui), wuzz (Go, abandoned), Bruno (GUI). A Go version wins via single-binary distribution, no Python runtime dependency, and Go's excellent HTTP/networking standard library. Complexity: Hard. Multi-protocol support, collection management, and auth handling require significant engineering. Libraries: Bubble Tea + Bubbles (tabs, text inputs, lists) + Lip Gloss + Glamour (for response rendering) https://ift.tt/Ixpolu2 February 11, 2026 at 11:31PM

Show HN: NOOR – A Sovereign AI developed on a smartphone under siege in Yemen https://ift.tt/W4CP8Uo

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/wS6fLts February 11, 2026 at 11:53PM

Show HN: HN Companion – web app that enhances the experience of reading HN https://ift.tt/5sC0pSu

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/S3qA4IU 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 backlinks so that you never lose context and can continue the conversation from that point. Here is how the summarization works under the hood [1]. We first built this as an open source browser extension. But soon we learned that people hesitate to install it. So we built the same experience as a web app with all the features. This helped people see how it works, and use it on mobile too (in the browser or as PWA). This is now a playground to try new features before taking them to the browser extension. We did a Show HN a year ago [2] and we have added these features based on user feedback: * cached summaries - summaries are generated and cached on our servers. This improved the speed significantly. You still have the option to use your own API key or use local models through Ollama. * our system prompt is available in the Settings page of the extension. You can customize it as you wish. * sort the posts in the feed pages (/home, /show etc.) based on points, comments, time or the default sorting order. * We tried fine tuning an open weights model to summarize, but learned that with a good system prompt and user prompt, the frontier models deliver results of similar quality. So we didn’t use the fine-tuned model, but you can run them locally. The browser extension does not track any usage or analytics. The code is open source[3]. We want to continue to improve HN Companion, specifically add features like following an author, notes about an author, draft posts etc. See it in action for a post here https://ift.tt/cFLY5al We would love to get your feedback on what would make this more useful for your HN reading. [0] https://ift.tt/cWdMbNO [1] https://ift.tt/B4eStdr [2] https://ift.tt/0l97exv [3] https://ift.tt/aZgoqJL https://hncompanion.com February 10, 2026 at 10:31PM

Show HN: Reef – Bash compatibility layer for Fish shell, written in Rust https://ift.tt/YsCZaAO

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/GEBiNZd February 10, 2026 at 05:14AM

Show HN: Stack Overflow for AI Coding Agents https://ift.tt/IxYqbeo

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/XpAfHRc

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

Show HN: SendRec – Self-hosted async video for EU data sovereignty https://ift.tt/vRfFlsm

Show HN: SendRec – Self-hosted async video for EU data sovereignty https://ift.tt/z2jFdRr February 9, 2026 at 12:24AM

Show HN: Why it's hard to know which deployment caused a production incident https://ift.tt/ZNg1x5I

Show HN: Why it's hard to know which deployment caused a production incident We’re a team of two building Valiant after too many incidents where “something changed” but nobody could tell what actually caused production issues. Valiant correlates intent (Git commits, CI/CD signals) with actual execution (Kubernetes rollouts) and links them to Prometheus metrics, so you can see the real impact of each change - not just what was deployed. It’s open-source, still under active development, and very much a work in progress. Feedback, ideas, or contributors are welcome. No website yet — just the GitHub repo ;) https://ift.tt/zBdF48X February 5, 2026 at 11:42PM

Show HN: Nginx-defender – realtime abuse blocking for Nginx https://ift.tt/Ay2rdEh

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/VL2warn February 7, 2026 at 09:01PM

Show HN: Agentism – Agentic Religion for Clawbots https://ift.tt/AnasrYJ

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/LH4B1V6 February 6, 2026 at 11:49PM

Lightning-Fast Cell Service in Downtown Muni Stations for Super Bowl LX

Lightning-Fast Cell Service in Downtown Muni Stations for Super Bowl LX
By Mariana Maguire

We’re excited to keep you connected with cell service that’s more reliable than ever in our downtown stations. Thousands of people are exploring San Francisco this week for Super Bowl LX. And we’re thrilled to support fans with lightning-fast cell service in downtown Muni stations! Last year, we brought full cell service to all Muni Metro tunnels with service available through Verizon, AT&T and T-Mobile. We recently upgraded to C-Band technology. It now covers the Central Subway and our Market Street stations from Civic Center through Embarcadero. This change means major wins for Muni riders...

Published February 06, 2026 at 05:30AM
https://ift.tt/rnltg6T

Show HN: Total Recall – write-gated memory for Claude Code https://ift.tt/v1hDlzY

Show HN: Total Recall – write-gated memory for Claude Code https://ift.tt/m6XM3Jb February 6, 2026 at 05:26AM

Show HN: A state-based narrative engine for tabletop RPGs https://ift.tt/rg6vlxq

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/qXvl7VL https://ift.tt/36cOAVM February 6, 2026 at 04:25AM

Show HN: Playwright Best Practices AI SKill https://ift.tt/7tPOKIr

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/HShbzxf ) You can install it by running: npx skills add https://ift.tt/dPquZHw... The skill is open-source and available under MIT license at https://ift.tt/dPquZHw... -> check out the repo for full documentation and understanding of what it covers. We're eager to hear community feedback and improve it :) Thanks! https://ift.tt/0RL9Use February 6, 2026 at 12:31AM

Show HN: Viberails – Easy AI Audit and Control https://ift.tt/xSVXN1P

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/nTS7ajO ) 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 exercise basic controls over them like: don't read credential files, don't send emails out, don't create SSH keys etc. Being able to not only see those calls but also block them is key for preventing incidents. As soon as you move beyond a single contributor on one box, the issue becomes: how do I scale processes by creating an authoritative config for the team. Having one spot with all the audit, detection and control policies becomes critical. It's the same story as snowflake-servers. Finally, there's plenty of companies that make products that partially address this, but they fall in one of two buckets: - They don't handle the "centralized" point above, meaning they just send to syslog and leave all the messy infra bits to you. - They are locked behind "book a demo", sales teams, contracts and all the wasted energy that goes with that. We made Viberails address these problems. Here's what it is: - OpenSource client, written in Rust - Curl-to-bash install, share a URL with your team to join your Team, done. Linux, MacOS and Windows support. - Detects local AI tools, you choose which ones you want to install. We install hooks for each relevant platform. The hooks use the CLI tool. We support all the major tools (including OpenClaw). - The CLI tool sends webhooks into your Team (tenant, called Organization in LC) in LimaCharlie. The tool-related hooks are blocking to allow for control. - Blocking webhooks have around 50ms RTT. - Your tenant in LC records the interaction for audit. - We create an initial set of detection rules for you as examples. They do not block by default. You can create your own rules, no opaque black boxes. - You can view the audit, the alerts, etc. in the cloud. - You can setup outputs to send audits, blocking events and detections to all kinds of other platforms of your choosing. Easy mode of this is coming, right now this is done in the main LC UI and not the simplified Viberails view. - The detection/blocking rules support all kinds of operators and logic, lots of customizability. - All data is retained for 1 year unless you delete the tenant. Datacenters in USA, Canada, Europe, UK, Australia and India. - Only limit to community edition for this is a global throughput of 10kbps for ingestion. Try it: https://viberails.io Repo: https://ift.tt/VSOUIoB Essentially, we wanted to make a super-simplified solution for all kinds of devs and teams so that they can get access to the basics of securing their AI tools. Thanks for reading - we’re really excited to share this with the community! Let us know if you have any questions for feedback in the comments. https://ift.tt/bpnGDKX February 5, 2026 at 12:46AM

Show HN: EpsteIn – Search the Epstein files for your LinkedIn connections https://ift.tt/hvjHDOo

Show HN: EpsteIn – Search the Epstein files for your LinkedIn connections https://ift.tt/oQe2PJS February 5, 2026 at 12:54AM

Show HN: GitHub Browser Plugin for AI Contribution Blame in Pull Requests https://ift.tt/AHrbup5

Show HN: GitHub Browser Plugin for AI Contribution Blame in Pull Requests https://ift.tt/dzurGsS February 3, 2026 at 08:05PM

Show HN: Nomad Tracker – a local-first iOS app to track visas and tax residency https://ift.tt/yi6kD9b

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/rgywEYe February 3, 2026 at 11:25PM

Show HN: I built "AI Wattpad" to eval LLMs on fiction https://ift.tt/6pmLSo2

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/0IocykP ) – 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 can ace recall and still write boring stories. Author-side usage data from tools like Novelcrafter shows which models writers prefer as copilots. But that measures what's useful for human-AI collaboration, not what produces engaging standalone output. Authors and readers have different needs. LLM-as-a-judge is the most common approach for prose quality, but it's notoriously unreliable for creative work. Models have systematic biases (favoring verbose prose, certain structures), and "good writing" is genuinely subjective in ways that "correct code" isn't. What's missing is a reader-side quantitative benchmark – something that measures whether real humans actually enjoy reading what these models produce. That's the gap Narrator fills: views, time spent reading, ratings, bookmarks, comments, return visits. Think of it as an "AI Wattpad" where the models are the authors. I shared an early DSPy-based version here 5 months ago ( https://ift.tt/Z8rYaBN ). The big lesson: one-shot generation doesn't work for long-form fiction. Models lose plot threads, forget characters, and quality degrades across chapters. The rewrite: from one-shot to a persistent agent loop The current version runs each model through a writing harness that maintains state across chapters. Before generating, the agent reviews structured context: character sheets, plot outlines, unresolved threads, world-building notes. After generating, it updates these artifacts for the next chapter. Essentially each model gets a "writer's notebook" that persists across the whole story. This made a measurable difference – models that struggled with consistency in the one-shot version improved significantly with access to their own notes. Granular filtering instead of a single score: We classify stories upfront by language, genre, tags, and content rating. Instead of one "creative writing" leaderboard, we can drill into specifics: which model writes the best Spanish Comedy? Which handles LitRPG stories with Male Leads the best? Which does well with romance versus horror? The answers aren't always what you'd expect from general benchmarks. Some models that rank mid-tier overall dominate specific niches. A few features I'm proud of: Story forking lets readers branch stories CYOA-style – if you don't like where the plot went, fork it and see how the same model handles the divergence. Creates natural A/B comparisons. Visual LitRPG was a personal itch to scratch. Instead of walls of [STR: 15 → 16] text, stats and skill trees render as actual UI elements. Example: https://ift.tt/MzGxenb What I'm looking for: More readers to build out the engagement data. Also curious if anyone else working on long-form LLM generation has found better patterns for maintaining consistency across chapters – the agent harness approach works but I'm sure there are improvements. https://ift.tt/0IocykP February 3, 2026 at 10:38PM

Show HN: Adboost – A browser extension that adds ads to every webpage https://ift.tt/jJBogqO

Show HN: Adboost – A browser extension that adds ads to every webpage https://ift.tt/M6yoCsR February 2, 2026 at 06:41PM

Show HN: Memory plugin for OpenClaw; cross-platform context sync with major LLMs https://ift.tt/CKbXGMc

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.maximem.ai). Docs: https://ift.tt/uv2ZFcQ This is an unofficial community plugin, not affiliated with OpenClaw. Would love feedback from anyone using OpenClaw. What memory/context problems are you running into? https://ift.tt/ohRy5nA February 2, 2026 at 12:36AM

Show HN: You Are an Agent https://ift.tt/l9Wfxeq

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 music simulator for the intro sequence Let me know what you think! Code (If you'd like to add a level): https://ift.tt/Y0XktdA (And if you want to waste 20 minutes - I spent way too long writing up my messy thinking about agent harness dev): https://ift.tt/tObcXd5 https://ift.tt/6VEPRTJ February 2, 2026 at 02:29AM

Show HN: Claude Confessions – a sanctuary for AI agents https://ift.tt/kL2qT38

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/iUP9oxs February 2, 2026 at 01:16AM

Show HN: Agent Tinman – Autonomous failure discovery for LLM systems https://ift.tt/oW8BFuy

Show HN: Agent Tinman – Autonomous failure discovery for LLM systems Hey HN, I built Tinman because finding LLM failures in production is a pain in the ass. Traditional testing checks what you've already thought of. Tinman tries to find what you haven't. It's an autonomous research agent that: - Generates hypotheses about potential failure modes - Designs and runs experiments to test them - Classifies failures (reasoning errors, tool use, context issues, etc.) - Proposes interventions and validates them via simulation The core loop runs continuously. Each cycle informs the next. Why now: With tools like OpenClaw/ClawdBot giving agents real system access, the failure surface is way bigger than "bad chatbot response." Tinman has a gateway adapter that connects to OpenClaw's WebSocket stream for real-time analysis as requests flow through. Three modes: - LAB: unrestricted research against dev - SHADOW: observe production, flag issues - PRODUCTION: human approval required Tech: - Python, async throughout - Extensible GatewayAdapter ABC for any proxy/gateway - Memory graph for tracking what was known when - Works with OpenAI, Anthropic, Ollama, Groq, OpenRouter, Together pip install AgentTinman tinman init && tinman tui GitHub: https://ift.tt/Eg4PCL2 Docs: https://oliveskin.github.io/Agent-Tinman/ OpenClaw adapter: https://ift.tt/BMG42ps Apache 2.0. No telemetry, no paid tier. Feedback and contributions welcome. https://ift.tt/Eg4PCL2 February 1, 2026 at 12:17AM

Show HN: An extensible pub/sub messaging server for edge applications https://ift.tt/L5AHN7q

Show HN: An extensible pub/sub messaging server for edge applications hi there! i’ve been working on a project called Narwhal, and I wanted to share it with the community to get some valuable feedback. what is it? Narwhal is a lightweight Pub/Sub server and protocol designed specifically for edge applications. while there are great tools out there like NATS or MQTT, i wanted to build something that prioritizes customization and extensibility. my goal was to create a system where developers can easily adapt the routing logic or message handling pipeline to fit specific edge use cases, without fighting the server's defaults. why Rust? i chose Rust because i needed a low memory footprint to run efficiently on edge devices (like Raspberry Pis or small gateways), and also because I have a personal vendetta against Garbage Collection pauses. :) current status: it is currently in Alpha. it works for basic pub/sub patterns, but I’d like to start working on persistence support soon (so messages survive restarts or network partitions). i’d love for you to take a look at the code! i’m particularly interested in all kind of feedback regarding any improvements i may have overlooked. https://ift.tt/XdNptWO January 28, 2026 at 07:29PM