🛠️ All DevTools

[API/SDK] Show HN: UltraContext – A simple context API for AI agents with auto-versioning Hey HN! I&#x27;m Fabio and I built UltraContext, a simple context API for AI agents with automatic versioning.<p>After two years building AI agents in production, I experienced firsthand how frustrating it is to manage context at scale. Storing messages, iterating system prompts, debugging behavior and multi-agent patterns—all while keeping track of everything without breaking anything. It was driving me insane.<p>So I built UltraContext. The mental model is git for context:<p>- Updates and deletes automatically create versions (history is never lost)<p>- Replay state at any point<p>The API is 5 methods:<p><pre><code> uc.create() &#x2F;&#x2F; new context (can fork from existing) uc.append() &#x2F;&#x2F; add message uc.get() &#x2F;&#x2F; retrieve by version, timestamp, or index uc.update() &#x2F;&#x2F; edit message → creates version uc.delete() &#x2F;&#x2F; remove message → creates version </code></pre> Messages are schema-free. Store conversation history, tool calls, system prompts—whatever shape you need. Pass it straight to your LLM using any framework you&#x27;d like.<p>What it&#x27;s for:<p>- Persisting conversation state across sessions<p>- Debugging agent behavior (rewind to decision point)<p>- Forking contexts to test different flows<p>- Audit trails without building audit infrastructure<p>- Multi-agent and sub-agent patterns<p>What it&#x27;s NOT:<p>- Not a memory&#x2F;RAG system (no semantic search)<p>- Not a vector database<p>- Not an Orchestration&#x2F;LLM framework<p>UltraContext handles versioning, branching, history. You get time-travel with one line.<p>Docs: <a href="https:&#x2F;&#x2F;ultracontext.ai&#x2F;docs" rel="nofollow">https:&#x2F;&#x2F;ultracontext.ai&#x2F;docs</a><p>Early access: <a href="https:&#x2F;&#x2F;ultracontext.ai" rel="nofollow">https:&#x2F;&#x2F;ultracontext.ai</a><p>Would love feedback! Especially from anyone who&#x27;s rolled their own context engineering and can tell me what I&#x27;m missing.

[Other] Nested Code Fences in Markdown

[Other] Predict npm package abandonment before it breaks your build Predict which npm and Python dependencies are at risk of abandonment. Get health scores and risk assessments for your packages.

[Other] The best full-stack templates that empower developers App Starter is a comprehensive application template that provides a solid foundation for building modern web applications with authentication, real-time features, and a sleek user interface.

[Other] Show HN: Generate animated solar system timelapse videos for any date range A fork of Solar System Live that generates animated videos showing planetary orbits over any date range. Tracks orbital statistics (how many times Earth was lapped by Mercury&#x2F;Venus, or lapped outer planets) and overlays dates&#x2F;ages on each frame.<p>Example: Einstein&#x27;s lifetime (1879-1955) showing 76 years of solar system evolution. Built with Python + Pillow + ffmpeg, runs locally with Lighttpd.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;simondorfman&#x2F;solar_system_live" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;simondorfman&#x2F;solar_system_live</a>

[Other] Show HN: macOS native DAW with Git branching model I am working on building (and have made my first prerelease) for a Digital Audio Workstation with git like branching version control.<p>It&#x27;s free for local use and paid for cloud syncing or collaboration.

[Other] Claude Chill: Fix Claude Code's flickering in terminal

[CLI Tool] Show HN: Fence – Sandbox CLI commands with network/filesystem restrictions Hi HN!<p>Fence wraps any command in a sandbox that blocks network by default and restricts filesystem writes. Useful for running semi-trusted code (package installs, build scripts, unfamiliar repos) with controlled side effects, or even just blocking tools that phone home.<p>&gt; fence curl <a href="https:&#x2F;&#x2F;example.com" rel="nofollow">https:&#x2F;&#x2F;example.com</a> # -&gt; blocked<p>&gt; fence -t code -- npm install # -&gt; template with registries allowed<p>&gt; fence -m -- npm install # -&gt; monitor mode: see what gets blocked<p>One use-case is to use it with AI coding agents to reduce the risk of running agents with fewer interactive permission prompts:<p>&gt; fence -t code -- claude --dangerously-skip-permissions<p>You can import existing Claude Code permissions with `fence import --claude`.<p>Fence uses OS-native sandboxing (macOS sandbox-exec, Linux bubblewrap) + local HTTP&#x2F;SOCKS proxies for domain filtering.<p>Why I built this: I work on Tusk Drift, a system to record and replay real traffic as API tests (<a href="https:&#x2F;&#x2F;github.com&#x2F;Use-Tusk&#x2F;tusk-drift-cli" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Use-Tusk&#x2F;tusk-drift-cli</a>). I needed a way to sandbox the service under test during replays to block localhost outbound connections (Postgres, Redis) and force the app to use mocks instead of real services. I quickly realized that this could be a general purpose tool that would also be useful as a permission manager across CLI agents.<p>Limitations: Not strong containment against malware. Proxy-based filtering requires programs to respect `HTTP_PROXY`.<p>Curious if others have run into similar needs, and happy to answer any questions!

[API/SDK] Show HN: Mastra 1.0, open-source JavaScript agent framework from the Gatsby devs Hi HN, we&#x27;re Sam, Shane, and Abhi.<p>Almost a year ago, we first shared Mastra here (<a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=43103073">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=43103073</a>). It’s kind of fun looking back since we were only a few months into building at the time. The HN community gave a lot of enthusiasm and some helpful feedback.<p>Today, we released Mastra 1.0 in stable, so we wanted to come back and talk about what’s changed.<p>If you’re new to Mastra, it&#x27;s an open-source TypeScript agent framework that also lets you create multi-agent workflows, run evals, inspect in a local studio, and emit observability.<p>Since our last post, Mastra has grown to over 300k weekly npm downloads and 19.4k GitHub stars. It’s now Apache 2.0 licensed and runs in prod at companies like Replit, PayPal, and Sanity.<p>Agent development is changing quickly, so we’ve added a lot since February:<p>- Native model routing: You can access 600+ models from 40+ providers by specifying a model string (e.g., `openai&#x2F;gpt-5.2-codex`) with TS autocomplete and fallbacks. - Guardrails: Low-latency input and output processors for prompt injection detection, PII redaction, and content moderation. The tricky thing here was the low-latency part. - Scorers: An async eval primitive for grading agent outputs. Users were asking how they should do evals. We wanted to make it easy to attach to Mastra agents, runnable in Mastra studio, and save results in Mastra storage. - Plus a few other features like AI tracing (per-call costing for Langfuse, Braintrust, etc), memory processors, a `.network()` method that turns any agent into a routing agent, and server adapters to integrate Mastra within an existing Express&#x2F;Hono server.<p>(That last one took a bit of time, we went down the ESM&#x2F;CJS bundling rabbithole, ran into lots of monorepo issues, and ultimately opted for a more explicit approach.)<p>Anyway, we&#x27;d love for you to try Mastra out and let us know what you think. You can get started with `npm create mastra@latest`.<p>We&#x27;ll be around and happy to answer any questions!

[API/SDK] Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API

[Other] Workspaces and Monorepos in Package Managers

[API/SDK] Build your backend in 5 minutes, not 5 months API grid provides a developer platform that enables teams to immediately get production-ready API without any need to build or maintain any backend infrastructure. Only activate the endpoints which you require, charge per request, keep an eye on utilization, mistakes, and latency in real-time, and scale easily. Created for startups, agencies, and product teams, capable to ship faster and with less overhead.

[Code Quality] Analyze Any GitHub Profile Instant code quality analysis for GitHub profiles. Discover your true developer score. Uncover hidden strengths. Stand out to recruiters and collaborators. Analyze any developer's GitHub activity, languages, and expertise in seconds. Get instant insights into code quality, activity, and expertise

[API/SDK] Instant crypto address validation for 120+ chains. Validate cryptocurrency addresses across 100+ blockchain networks instantly. Secure, lightweight, and developer-friendly REST API.

[Code Quality] Show HN: LangGraph architecture that scales (hexagonal pattern, 110 tests) I kept hitting the same wall with LangGraph: tutorials show you how to build a graph, not how to maintain one when you have 8 nodes, 3 agents, and shared state across subgraphs.<p>So I built a reference architecture with: - Platform layer separation (framework-independent core) - Contract validation on every state mutation - 110 tests including architecture boundary enforcement - Patterns that AI coding agents can&#x27;t accidentally break<p>Repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;cleverhoods&#x2F;sagecompass" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;cleverhoods&#x2F;sagecompass</a> Wrote about the patterns: <a href="https:&#x2F;&#x2F;dev.to&#x2F;cleverhoods&#x2F;from-prompt-to-platform-architecture-rules-i-use-59gp" rel="nofollow">https:&#x2F;&#x2F;dev.to&#x2F;cleverhoods&#x2F;from-prompt-to-platform-architect...</a><p>It&#x27;s MIT licensed. Would love feedback on the approach - especially from anyone who&#x27;s scaled LangGraph past the tutorial stage.

[Other] Linux kernel framework for PCIe device emulation, in userspace

[Other] KAOS – The Kubernetes Agent Orchestration System

[Other] Show HN: Txt2plotter – True centerline vectors from Flux.2 for pen plotters I’ve been working on a project to bridge the gap between AI generation and my AxiDraw, and I think I finally have a workflow that avoids the usual headaches.<p>If you’ve tried plotting AI-generated images, you probably know the struggle: generic tracing tools (like Potrace) trace the <i>outline</i> of a line, resulting in double-strokes that ruin the look and take twice as long to plot.<p>What I tried previously:<p>- Potrace &#x2F; Inkscape Trace: Great for filled shapes, but results in &quot;hollow&quot; lines for line art.<p>- Canny Edge Detection: Often too messy; it picks up noise and creates jittery paths.<p>- Standard SDXL: Struggled with geometric coherence, often breaking lines or hallucinating perspective.<p>- A bunch of projects that claimed to be txt2svg but which produced extremely poor results, at least for pen plotting. (Chat2SVG, StarVector, OmniSVG, DeepSVG, SVG-VAE, VectorFusion, DiffSketcher, SVGDreamer, SVGDreamer++, NeuralSVG, SVGFusion, VectorWeaver, SwiftSketch, CLIPasso, CLIPDraw, InternSVG)<p>My Approach:<p>I ended up writing a Python tool that combines a few specific technologies to get a true &quot;centerline&quot; vector:<p>1. Prompt Engineering: An LLM rewrites the prompt to enforce a &quot;Technical Drawing&quot; style optimized for the generator.<p>2. Generation: I&#x27;m using Flux.2-dev (4-bit). It seems significantly better than SDXL at maintaining straight lines and coherent geometry.<p>3. Skeletonization: This is the key part. Instead of tracing contours, I use Lee’s Method (via scikit-image) to erode the image down to a 1-pixel wide skeleton. This recovers the actual stroke path.<p>4. Graph Conversion: The pixel skeleton is converted into a graph to identify nodes and edges, pruning out small artifacts&#x2F;noise.<p>5. Optimization: Finally, I feed it into vpype to merge segments and sort the paths (TSP) so the plotter isn&#x27;t jumping around constantly.<p>You can see the results in the examples inside the Github repo.<p>The project is currently quite barebones, but it produces better results than other options I&#x27;ve tested so I&#x27;m publishing it. I&#x27;m interested in implementing better pre&#x2F;post processing, API-based generation, and identifying shapes for cross-hatching.

[Other] Show HN: Subth.ink – write something and see how many others wrote the same Hey HN, this is a small Haskell learning project that I wanted to share. It&#x27;s just a website where you can see how many people write the exact same text as you (thought it was a fun idea).<p>It&#x27;s built using Scotty, SQLite, Redis and Caddy. Currently it&#x27;s running in a small DigitalOcean droplet (1 Gb RAM).<p>Using Haskell for web development (specifically with Scotty) was slightly easier than I thought, but still a relatively hard task compared to other languages. One of my main friction points was Haskell&#x27;s multiple string-like types: String, Text (&amp; lazy), ByteString (&amp; lazy), and each library choosing to consume a different one amongst these. There is also a soft requirement to learn monad transformers (e.g. to understand what liftIO is doing) which made the initial development more difficult.

[Other] Show HN: Pipenet – A Modern Alternative to Localtunnel Hey HN!<p>localtunnel&#x27;s server needs random ports per client. That doesn&#x27;t work on Fly.io or behind strict firewalls.<p>We rewrote it in TypeScript and added multiplexing over a single port. Open-source and 100% self-hostable.<p>Public instance at *.pipenet.dev if you don&#x27;t want to self-host.<p>Built at Glama for our MCP Inspector, but it&#x27;s a generic tunnel with no ties to our infra.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;punkpeye&#x2F;pipenet" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;punkpeye&#x2F;pipenet</a>