🛠️ All DevTools

[Other] Download all of your GitHub data

[Other] Show HN: HyprMCP – Analytics, logs and auth for MCP servers Hi HN, my name is Philip, I’m the co-founder of Glasskube and one of the creators of HyprMCP.<p>This project started when we did what everyone was doing — building a remote MCP server and launching it. Building the first local MCP server for testing was quite simple, and we had our first tools ready within a day. The next step was turning that into a production-ready remote MCP server.<p>As we exposed the MCP server to our users, we wanted to authenticate them with our existing authentication methods. We dove deep into authentication. Our approach was to build an auth proxy and plug it in front of our MCP. It took a while to figure out Dynamic Client Registration (DCR) and the OAuth spec, and especially the gaps between existing OIDC IDPs and what LLM clients needed.<p>We thought authentication would be the hard part — but it wasn’t. When we shared the MCP server with a few friendly startups, we realized that different MCP clients behave differently. Especially if something didn&#x27;t work, it was hard to figure out the root cause. We ended up storing all the raw gRPC method calls to see if the initialization and subsequent requests worked. This is especially useful if you are on a serverless environment with limited debugging functionality, like Cloudflare Workers.<p>Once we solved auth and compatibility, we launched to a small customer base — done, right? Unfortunately, not quite. Technically everything was working, but when we started talking to users, they told us the MCP server didn’t always respond with the right tools for their prompts. We had a working enterprise-grade MCP server — but it wasn’t very smart. After talking to some startup friends, we realized we needed an evaluation layer. That’s when we added prompt analytics — letting us see which prompts triggered which tools and how well they performed. That alone dramatically improved our MCP’s behavior and overall user experience.<p>After building all of this into our proxy, we realized that everyone building a remote MCP was facing the same challenges. So we decided to package it all up and release it to the community.<p>We’re thrilled to launch and open-source HyprMCP. It acts as a proxy that you can plug in front of your MCP server(s) with zero code changes. You get authentication, logging and debugging, prompt analytics, and an MCP connection instructions generator.<p>Under the hood, HyprMCP leverages dynamic Kubernetes Operators (Metacontroller) to automate infrastructure provisioning.<p>On the roadmap: MCP aggregation — combining multiple MCP servers under one single remote URL for large organizations running servers with different lifecycles. All of it without storing end user credentials on the server and connecting the MCP to the organizations existing authentication methods.<p>You can check the project out on GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;hyprmcp&#x2F;jetski" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;hyprmcp&#x2F;jetski</a><p>For testing, we also have a hosted version here: <a href="https:&#x2F;&#x2F;app.hyprmcp.com" rel="nofollow">https:&#x2F;&#x2F;app.hyprmcp.com</a><p>We even created a demo video on YouTube: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=m2-YyfjXap4" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=m2-YyfjXap4</a><p>We’d love to get your feedback, hear what features are missing, and learn how you’re building and running your own MCP servers.

[CLI Tool] Show HN: A Lisp Interpreter for Shell Scripting Redstart is a lightweight Lisp interpreter written in C++ with a focus on shell scripting. It lets you combine the expressive power of Lisp with the practicality of the Unix shell: you can run commands, capture output, pipe between processes, and still use Lisp syntax for logic and structure. Think of it as writing your shell scripts in Lisp instead of Bash.

[API/SDK] Show HN: Twoway, a Go package for HPKE encrypted request-response flows Hey HN,<p>I&#x27;m Willem from Confident Security, we&#x27;ve built CONFSEC, a provably private AI inference engine. Today, we&#x27;re excited to open-source twoway: <a href="https:&#x2F;&#x2F;github.com&#x2F;confidentsecurity&#x2F;twoway" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;confidentsecurity&#x2F;twoway</a><p>twoway is a Go package that makes it easy to implement secure, encrypted request-response flows. It powers CONFSEC&#x27;s blind prompt handling, ensuring no one, not even us, can see client requests.<p>We built twoway on Cloudflare&#x27;s circl&#x2F;hpke, it uses Hybrid Public key Encryption to implement two flows: - A one-to-one flow where a sender communicates with a single receiver. This flow is fully compatible with RFC 9458 Oblivious HTTP (OHTTP), and the chunked OHTTP draft RFC. - A one-to-many flow where a sender communicates with one or more receivers. Similar to the Apple&#x27;s PCC&#x27;s request flow.<p>Other features include: - Compatibility with any transport, twoway deals with just the messages. - Chunked messages. - Allows for custom HPKE implementations for specialized needs like cryptographic hardware modules.<p>Our README has clear examples to get you started, all you need to do is go get and try an encrypted &quot;Hello world&quot; exchange.<p>Our team will be popping in to answer questions, we&#x27;d love to hear your feedback.<p>Cheers! Willem

[Other] Show HN: Vincent – A delegation framework for wallet automation Vincent lets users safely grant apps&#x2F;agents limited, revocable permission to use their wallets. Think “OAuth for crypto actions”: you define scopes (e.g., “rebalance stables on Aave up to $1k&#x2F;day”), users approve, and your app runs within on-chain guardrails. Non-custodial. Built with Lit Protocol&#x27;s decentralized programmable signing.

[Other] Show HN: FleetCode – Open-source UI for running multiple coding agents Hi HN! I&#x27;ve recently been finding productivity in running parallel CLI coding agents(after not believing in them initially).<p>After having to do a ton of git stashing and branch fumbling, I decided I needed to something to more ergonomically run these agents in their own dedicated spaces.<p>I tried a lot of the existing products but they either were too convoluted or flat out didn&#x27;t work. Some of them also seem to roll their own chat UI which I don&#x27;t think is the right approach, I wanted to something to lightly wrap my terminal sessions.<p>So I built FleetCode! It uses git worktrees and let&#x27;s you run multiple agents at once. It&#x27;s made my multi agent coding workflow much easier.<p>It&#x27;s free and open source, would love some feedback!

[DevOps] Show HN: Solving the cluster 1 problem with vCluster standalone vcluster is an open source tool for Kubernetes multi tenancy and over the years it has matured to have hosted controlplane virtual cluster, shared virtual clusters but the host cluster problem was always there. With vcluster standalone, you can now create the first cluster also with the same developer experience and consolidate the multiple vendor problem. With this, you can now use vcluster for entire multi tenancy spectrum. Feel free to discuss, happy to answer any questuons.

[Other] Show HN: Recall: Give Claude perfect memory with Redis-backed persistent context Hey HN! I&#x27;m José, and I built Recall to solve a problem that was driving me crazy.<p>The Problem: I use Claude for coding daily, but every conversation starts from scratch. I&#x27;d explain my architecture, coding standards, past decisions... then hit the context limit and lose everything. Next session? Start over.<p>The Solution: Recall is an MCP (Model Context Protocol) server that gives Claude persistent memory using Redis + semantic search. Think of it as long-term memory that survives context limits and session restarts.<p>How it works: - Claude stores important context as &quot;memories&quot; during conversations - Memories are embedded (OpenAI) and stored in Redis with metadata - Semantic search retrieves relevant memories automatically - Works across sessions, projects, even machines (if you use cloud Redis)<p>Key Features: - Global memories: Share context across all projects - Relationships: Link related memories into knowledge graphs - Versioning: Track how memories evolve over time - Templates: Reusable patterns for common workflows - Workspace isolation: Project A memories don&#x27;t pollute Project B<p>Tech Stack: - TypeScript + MCP SDK - Redis for storage - OpenAI embeddings (text-embedding-3-small) - ~189KB bundle, runs locally<p>Current Stats: - 27 tools exposed to Claude - 10 context types (directives, decisions, patterns, etc.) - Sub-second semantic search on 10k+ memories - Works with Claude Desktop, Claude Code, any MCP client<p>Example Use Case: I&#x27;m building an e-commerce platform. I told Claude once: &quot;We use Tailwind, prefer composition API, API rate limit is 1000&#x2F;min.&quot; Now every conversation, Claude remembers and applies these preferences automatically.<p>What&#x27;s Next (v1.6.0 in progress): - CI&#x2F;CD pipeline with GitHub Actions - Docker support for easy deployment - Proper test suite with Vitest - Better error messages and logging<p>Try it:<p>npm install -g @joseairosa&#x2F;recall # Add to claude_desktop_config.json # Start using persistent memory

[Other] Testing a compiler-driven full-stack web framework

[Other] Show HN: Baby's first international landline Hi HN,<p>As a weekend project, I hacked together a physical phone, a Raspberry Pi running Asterisk and Twilio, to let toddlers safely make international calls.<p>I’ve documented the setup in this write-up and published the code + Ansible playbooks on GitHub so others can replicate it.<p>I built this so kids of expats can easily stay in touch with family on other continents.<p>Would love feedback from anyone who’s worked on something similar or tries building this themselves!<p>writeup: <a href="https:&#x2F;&#x2F;wip.tf&#x2F;posts&#x2F;telefonefix-building-babys-first-international-landline&#x2F;" rel="nofollow">https:&#x2F;&#x2F;wip.tf&#x2F;posts&#x2F;telefonefix-building-babys-first-intern...</a> github repos: - <a href="https:&#x2F;&#x2F;github.com&#x2F;nbr23&#x2F;ansible-role-telefonefix" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;nbr23&#x2F;ansible-role-telefonefix</a> - <a href="https:&#x2F;&#x2F;github.com&#x2F;nbr23&#x2F;allo-wed" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;nbr23&#x2F;allo-wed</a>

[Other] Scaling request logging with ClickHouse, Kafka, and Vector

[Other] Show HN: Oh Yah – Routine management app I built for my sons Hi HN! I built Oh Yah! to help my sons (age 7 and 10) stick to daily routines without constant reminders. The core idea: minimal distractions during tasks by locking navigation when a timer is running, plus optional photo-based task completion for accountability<p>Built with React Native&#x2F;Expo and Firebase. The trickiest part was designing the UX to be simple enough for kids with minimal distractions while giving parents enough control – ended up with a task-definition system that lets parents create weekly schedules with daily toggles instead of duplicating tasks across days<p>It&#x27;s on the App Store now after a few months of dogfooding with my family. There&#x27;s a 1-month free trial, then it&#x27;s subscription-based. Would love feedback from other parents dealing with similar challenges

[Database] Database Linting and Analysis for PostgreSQL

[IDE/Editor] Build production-grade AI agents using natural language Promptius is an AI-powered development environment designed to build and deploy autonomous agents based on user prompts.

[API/SDK] Take control of your API traffic with custom rate limits. Enterprise-grade rate limiting service built on Cloudflare. Define rate limits by user ID, API key, or any custom parameter. Drop-in integration with ~25ms latency.

[Other] From idea to deployment—all on your enterprise data Build production-ready apps from natural language using your real data, in your cloud, with enterprise security and governance built in. Start building with AI that knows your stack.

[Other] Business & IT Technology WordPress Theme Techto is a modern, responsive WordPress theme for IT companies, startups, and agencies. With 24 demos, template library, and flexible inner pages, it combines sleek design with powerful functionality for your online presence.

[Testing] Stop breaking prod, build & test with a fleet of QA agents Get a fleet of QA agents that protect your product’s quality. Let AI explore your app for full test coverage, monitor staging to catch issues, and deliver debugging context as soon as you open your PRs. Build at full speed and never break prod again.

[Other] Remove checkered backgrounds instantly - 100% client-side Ever remove those annoying checkered patterns from screenshots and AI images ? "Remove BG" is a free, privacy-first web tool that instantly removes checkered patterns and solid backgrounds from your images - entirely in your browser. Built with Claude Code

[Other] The boilerplate with all you need to build your iOS Apps. AppForgeAI saves weeks of setup work, letting you ship MVPs and full-scale apps in record time. Whether you’re launching your next startup or your 10th indie app, you’ll start with production-ready code from day one.