🛠️ Hacker News Tools

[Other] Show HN: WebGPU enables local LLM in the browser – demo site with AI chat Browser LLM demo working on JavaScript and WebGPU. WebGPU is already supported in Chrome, Safari, Firefox, iOS (v26) and Android.<p>Demo, similar to ChatGPT <a href="https:&#x2F;&#x2F;andreinwald.github.io&#x2F;browser-llm&#x2F;" rel="nofollow">https:&#x2F;&#x2F;andreinwald.github.io&#x2F;browser-llm&#x2F;</a><p>Code <a href="https:&#x2F;&#x2F;github.com&#x2F;andreinwald&#x2F;browser-llm">https:&#x2F;&#x2F;github.com&#x2F;andreinwald&#x2F;browser-llm</a><p>- No need to use your OPENAI_API_KEY - its local model that runs on your device<p>- No network requests to any API<p>- No need to install any program<p>- No need to download files on your device (model is cached in browser)<p>- Site will ask before downloading large files (llm model) to browser cache<p>- Hosted on Github Pages from this repo - secure, because you see what you are running

[Other] Show HN: NaturalCron – Human-Readable Scheduling for .NET (With Fluent Builder) Hi HN!<p>I built NaturalCron because I was tired of writing and debugging CRON syntax like:<p><i>&#x2F;5 </i> * * 5<p>Now you can write something human-readable in .NET:<p>var expression = new NaturalCronExpression(&quot;every 5 minutes on friday&quot;);<p>Or use a Fluent Builder for strong typing and IDE support:<p>var expression = NaturalCronExpressionBuilder .Every().Minutes(5) .On(DayOfWeek.Friday) .Build();<p>Great for: - Code-based scheduling in .NET apps - Overriding schedules from configs or databases - Displaying easy-to-read rules in UIs<p>NuGet: <a href="https:&#x2F;&#x2F;www.nuget.org&#x2F;packages&#x2F;NaturalCron" rel="nofollow">https:&#x2F;&#x2F;www.nuget.org&#x2F;packages&#x2F;NaturalCron</a> GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;hugoj0s3&#x2F;NaturalCron">https:&#x2F;&#x2F;github.com&#x2F;hugoj0s3&#x2F;NaturalCron</a><p>Would love your feedback on syntax, builder design, and what features you&#x27;d like to see next!

[Other] Termagotchi – A terminal-based Tamagotchi simulation written in Go

[Other] Show HN: Agentic AI Frameworks on AWS (LangGraph,Strands,CrewAI,Arize,Mem0) We’ve published a set of open-source reference implementations on how to build production-grade Agentic AI applications on AWS.<p>What’s in the repo: • Agentic RAG, memory, and planning workflows with LangGraph &amp; CrewAI • Strands-based flows with observability using OTEL &amp; Arize • Evaluation with LLM-as-judge and cost&#x2F;performance regressions • Built with Bedrock, S3, Step Functions, and more<p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;aws-samples&#x2F;sample-agentic-frameworks-on-aws">https:&#x2F;&#x2F;github.com&#x2F;aws-samples&#x2F;sample-agentic-frameworks-on-...</a><p>Would love your thoughts — feedback, issues, and stars welcome!

[Other] Show HN: Schematra – Sinatra-inspired minimal web framework for Chicken Scheme I started this project a couple of weeks ago because I was stuck on my side project and needed some motivation. For a very long time I wanted to get back to do something useful in lisp&#x2F;scheme, did a quick research and settled on CHICKEN mostly because it&#x27;s relatively well maintained, fast enough, it&#x27;s extremely easy to build&#x2F;install and very easy to write interop to pretty much any library.<p>Most of the projects that I&#x27;ve written on the side have been using some combination of Sinatra + Sequel + Postgres&#x2F;Redis&#x2F;Something else + HTMX. I love the simplicity of Sinatra&#x27;s API so I decided to focus on trying to have a similar experience but in scheme, trying to make it ergonomic for a scheme dev (that part might not be there yet since I&#x27;m not an experienced scheme dev).<p>The most fun part was the dev cycle: Emacs + NREPL + Aider (as a code reviewer &amp; rubber ducky. For codegen it&#x27;s mostly annoying but works great for documentation &amp; refactoring).<p>I hope to add full SSE &amp; WebSocket support some time this week. Anyway, hopefully this is interesting to some of you and might be a source of fun :)

[Monitoring/Observability] Show HN: TraceRoot – Open-source agentic debugging for distributed services Hey Xinwei and Zecheng here, we are the authors of TraceRoot (<a href="https:&#x2F;&#x2F;github.com&#x2F;traceroot-ai&#x2F;traceroot">https:&#x2F;&#x2F;github.com&#x2F;traceroot-ai&#x2F;traceroot</a>).<p>TraceRoot (<a href="https:&#x2F;&#x2F;traceroot.ai">https:&#x2F;&#x2F;traceroot.ai</a>) is an open-source debugging platform that helps engineers fix production issues faster by combining structured traces, logs, source code contexts and discussions in Github PRs, issues and Slack channels, etc. with AI Agents.<p>At the heart are our lightweight Python (<a href="https:&#x2F;&#x2F;github.com&#x2F;traceroot-ai&#x2F;traceroot-sdk">https:&#x2F;&#x2F;github.com&#x2F;traceroot-ai&#x2F;traceroot-sdk</a>) and TypeScript (<a href="https:&#x2F;&#x2F;github.com&#x2F;traceroot-ai&#x2F;traceroot-sdk-ts">https:&#x2F;&#x2F;github.com&#x2F;traceroot-ai&#x2F;traceroot-sdk-ts</a>) SDKs - they can hook into your app using OpenTelemetry and captures logs and traces. These are either sent to a local Jaeger (<a href="https:&#x2F;&#x2F;www.jaegertracing.io&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.jaegertracing.io&#x2F;</a>) + SQLite backend or to our cloud backend, where we correlate them into a single view. From there, our custom agent takes over.<p>The agent builds a heterogeneous execution tree that merges spans, logs, and GitHub context into one internal structure. This allows it to model the control and data flow of a request across services. It then uses LLMs to reason over this tree - pruning irrelevant branches, surfacing anomalous spans, and identifying likely root causes. You can ask questions like “what caused this timeout?” or “summarize the errors in these 3 spans”, and it can trace the failure back to a specific commit, summarize the chain of events, or even propose a fix via a draft PR.<p>We also built a debugging UI that ties everything together - you explore traces visually, pick spans of interest, and get AI-assisted insights with full context: logs, timings, metadata, and surrounding code. Unlike most tools, TraceRoot stores long-term debugging history and builds structured context for each company - something we haven’t seen many others do in this space.<p>What’s live today:<p>- Python and TypeScript SDKs for structured logs and traces.<p>- AI summaries, GitHub issue generation, and PR creation.<p>- Debugging UI that ties everything together<p>TraceRoot is MIT licensed and easy to self-host (via Docker). We support both local mode (Jaeger + SQLite) and cloud mode. Inspired by OSS projects like PostHog and Supabase - core is free, enterprise features like agent mode multi-tenant and slack integration are paid.<p>If you find it interesting, you can see a demo video here: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=nb-D3LM0sJM" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=nb-D3LM0sJM</a><p>We’d love you to try TraceRoot (<a href="https:&#x2F;&#x2F;traceroot.ai">https:&#x2F;&#x2F;traceroot.ai</a>) and share any feedback. If you&#x27;re interested, our code is available here: <a href="https:&#x2F;&#x2F;github.com&#x2F;traceroot-ai&#x2F;traceroot">https:&#x2F;&#x2F;github.com&#x2F;traceroot-ai&#x2F;traceroot</a>. If we don’t have something, let us know and we’d be happy to build it for you. We look forward to your comments!

[Other] Show HN: Pontoon – Open-source customer data syncs Hi HN,<p>We’re Alex and Kalan, the creators of Pontoon (<a href="https:&#x2F;&#x2F;github.com&#x2F;pontoon-data&#x2F;Pontoon">https:&#x2F;&#x2F;github.com&#x2F;pontoon-data&#x2F;Pontoon</a>). Pontoon is an open-source data export platform that makes it really easy to create data syncs and send data to your enterprise customers. Check out our demo here: <a href="https:&#x2F;&#x2F;app.storylane.io&#x2F;share&#x2F;onova7c23ai6">https:&#x2F;&#x2F;app.storylane.io&#x2F;share&#x2F;onova7c23ai6</a> or try it out with docker: <a href="https:&#x2F;&#x2F;pontoon-data.github.io&#x2F;Pontoon&#x2F;getting-started&#x2F;quick-start&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pontoon-data.github.io&#x2F;Pontoon&#x2F;getting-started&#x2F;quick...</a><p>While at our prior roles as data engineers, we’ve both felt the pain of data APIs. We either had to spend weeks building out data pipelines in house or spend a lot on ETL tools like Fivetran (<a href="https:&#x2F;&#x2F;www.fivetran.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.fivetran.com&#x2F;</a>). However, there were a few companies that offered data syncs that would sync directly to our data warehouse (eg. Redshift, Snowflake, etc.), and when that was an option, we always chose it. This led us to wonder “Why don’t more companies offer data syncs?”. It turns out, building reliable cross-cloud data syncs is difficult. That’s why we built Pontoon.<p>We designed Pontoon to be:<p>- Easily deployed: we provide a single, self-contained Docker image for easy deployment and Docker Compose for larger workloads (<a href="https:&#x2F;&#x2F;pontoon-data.github.io&#x2F;Pontoon&#x2F;getting-started&#x2F;quick-start&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pontoon-data.github.io&#x2F;Pontoon&#x2F;getting-started&#x2F;quick...</a>)<p>- Support modern data warehouses: we support syncing to&#x2F;from Snowflake, BigQuery, Redshift, and Postgres.<p>- Sync cross cloud: sync from BigQuery to Redshift, Snowflake to BigQuery, Postgres to Redshift, etc.<p>- Developer friendly: data syncs can also be built via the API<p>- Open source: Pontoon is free to use by anyone<p>Under the hood, we use Apache Arrow (<a href="https:&#x2F;&#x2F;arrow.apache.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;arrow.apache.org&#x2F;</a>) to move data between sources and destinations. Arrow is very performant - we wanted to use a library that could handle the scale of moving millions of records per minute.<p>In the shorter-term, there are several improvements we want to make, like:<p>- Adding support for DBT models to make adding data models easier<p>- UX improvements like better error messaging and monitoring of data syncs<p>- More sources and destinations (S3, GCS, Databricks, etc.)<p>- Improve the API for a more developer friendly experience (it’s currently tied pretty closely to the front end)<p>In the longer-term, we want to make data sharing as easy as possible. As data engineers, we sometimes felt like second class citizens with how we were told to get the data we needed - “just loop through this api 1000 times”, “you probably won’t get rate limited” (we did), “we can schedule an email to send you a csv every day”. We want to change how modern data sharing is done and make it simple for everyone.<p>Give it a try <a href="https:&#x2F;&#x2F;github.com&#x2F;pontoon-data&#x2F;Pontoon">https:&#x2F;&#x2F;github.com&#x2F;pontoon-data&#x2F;Pontoon</a>. Cheers!

[IDE/Editor] Show HN: Kanban-style Phase Board: plan → execute → verify → commit After months of feedback from devs juggling multiple chat tools just to break big tasks into smaller steps, we re‑imagined our workflow as a Kanban‑style Phase Board right inside your favourite IDE. The new Phase mode turns any large task into a clean sequence of PR‑sized phases you can review and commit one by one.<p>How it works<p>1. Describe the goal (Task Query) – In Phase mode, type a concise description of what you want to build or change. Example: “Add rate‑limit middleware and expose a &#x2F;metrics endpoint.” Traycer treats this as the parent task. 2. Clarify intent (AI follow‑up) – Traycer may ask one or two quick questions (constraints, coding style). Answer them so the scope is crystal‑clear. 3. Auto‑generate the Phase Board – Traycer breaks the task into a sequential list of PR‑sized phases you can reorder, edit, or delete. 4. Open a phase &amp; generate its plan – get a detailed file‑level plan: which files, functions, symbols, and tests will be touched. 5. Handoff to your coding agent – Hit Execute to send that plan straight to Cursor, Claude Code, or any agent you prefer. 6. Verify the diff – When your agent finishes, Traycer compares the diff to the plan and checks compatibility with upcoming phases, flagging any mismatches. 7. Review &amp; commit (or tweak) – Approve and commit the phase, or adjust the plan and rerun. Then move on to the next phase.<p>Why it helps?<p>* True PR checkpoints – every phase is small enough to reason about and ship. * No runaway prompts – only the active phase is in context, so tokens stay low and results stay focused. * Tool-agnostic – Traycer plans and verifies; your coding agent writes code. * Fast course-correction – if something feels off, just edit that phase and re-run.<p>Try it out &amp; share feedback<p>Install the Traycer extension (<a href="https:&#x2F;&#x2F;traycer.ai&#x2F;installation" rel="nofollow">https:&#x2F;&#x2F;traycer.ai&#x2F;installation</a>), create a new task, and the Phase Board will appear. Add a few phases, run one through, and see how the PR‑sized checkpoints feel in practice. If you have suggestions that could make the flow smoother, drop them in the comments - every bit of feedback helps.

[API/SDK] Show HN: WhiteLightning – ultra-lightweight ONNX text classifiers trained w LLMs Hey HN,<p>We’re Volodymyr and Volodymyr—two developers from Ukraine building WhiteLightning. It’s a tool that turns large LLMs (Claude 4, Grok 4, GPT-4o via OpenRouter) into tiny ONNX text classifiers that run anywhere—even on drones at the edge.<p>Why we built this: Many developers want custom models (spam filters, sentiment analysis, PII detection, moderation tools), but don’t want to deal with constant API calls or deploy heavy models in production.<p>How it works: WhiteLightning uses LLMs to generate training data and distills it into KB-sized ONNX models you can run on any device and in any language. Just describe your task in a sentence, grab the ONNX model, and run it locally—Python, JS, Rust, Java, Swift, C++, you name it.<p>Try it instantly in your browser: <a href="https:&#x2F;&#x2F;whitelightning.ai&#x2F;playground.html" rel="nofollow">https:&#x2F;&#x2F;whitelightning.ai&#x2F;playground.html</a><p>Code &amp; docs: <a href="https:&#x2F;&#x2F;github.com&#x2F;Inoxoft&#x2F;whitelightning">https:&#x2F;&#x2F;github.com&#x2F;Inoxoft&#x2F;whitelightning</a><p>Community model library: <a href="https:&#x2F;&#x2F;github.com&#x2F;Inoxoft&#x2F;whitelightning-model-library">https:&#x2F;&#x2F;github.com&#x2F;Inoxoft&#x2F;whitelightning-model-library</a><p>We’d love your feedback—what works, what doesn’t, and what to improve.

[Other] Replacing tmux in my dev workflow

[CLI Tool] Show HN: Gmap: Explore Git Repos Visually from the CLI I built gmap, a command-line tool to visualize Git activity, weekly heatmaps, file churn, authorship stats, and more, right from your terminal.<p>Install with: cargo install gmap<p>Or on Arch via AUR: yay -S gmap<p>Repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;seeyebe&#x2F;gmap">https:&#x2F;&#x2F;github.com&#x2F;seeyebe&#x2F;gmap</a><p>Feedback is welcome. Contributions too. if you’re into Git internals, CLIs, or terminal UX.

[DevOps] Show HN: KubeForge – A GUI for Kubernetes YAMLs Hey HN,<p>I&#x27;m Brandon, a solo dev, and I built KubeForge - a visual editor for Kubernetes deployments that helps you build and validate YAML configs.<p>Origin Story: Over the past couple weeks, I got fed up manually writing Kubernetes YAMLs, especially when working with nested structures like containers, env, and volumeMounts. Even small typos or misaligned fields added lost time to broken deploys.<p>So I started hacking together a tool to visualize the structure of Kubernetes objects based on the OpenAPI schema. That prototype quickly turned into a full manifest builder.<p>What KubeForge does:<p>- Pulls the latest Kubernetes OpenAPI schema (auto-updated daily)<p>- Generates field-level forms with type safety, required fields, and smart defaults<p>- Lets you visually build manifests like a flow editor<p>- Outputs clean, deploy-ready YAML, with multi-object exports<p>Personally, I wanted a tool that:<p>- Validates fields as I build, not after deployment<p>- Surfaces nested fields, tooltips, and types without switching tabs<p>- Lets me export or share real YAMLs easily<p>Try it out:<p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;kubenote&#x2F;KubeForge">https:&#x2F;&#x2F;github.com&#x2F;kubenote&#x2F;KubeForge</a><p>Live demo: <a href="https:&#x2F;&#x2F;demo.kubefor.ge" rel="nofollow">https:&#x2F;&#x2F;demo.kubefor.ge</a><p>Website: <a href="https:&#x2F;&#x2F;kubefor.ge" rel="nofollow">https:&#x2F;&#x2F;kubefor.ge</a><p>It’s free and open source. I’d love feedback, bug reports, or ideas. Contributions welcome too .<p>Thanks, Brandon

[Other] A memory safe C framework, RAII, I/O, coroutine and other concurrency primitives

[Other] Show HN: Zero Waste Cloud – Finds 20-40% savings in AWS/GCP bills and CO2 impact Hey HN! I&#x27;m Mike, based in Stockholm&#x2F;Sweden and I&#x27;m the founder of Zero Waste Cloud (<a href="https:&#x2F;&#x2F;zerowastecloud.io" rel="nofollow">https:&#x2F;&#x2F;zerowastecloud.io</a>) - a tool that scans AWS and GCP infrastructure to find cost optimization opportunities while calculating the environmental impact. Almost all businesses can save 20-40% of their cloud costs using this tool (sources at bottom)<p>TLDR: Sign up -&gt; Connect your AWS&#x2F;GCP -&gt; Scan -&gt; Save 20-40% of your cloud spend.<p>My backstory: I&#x27;ve been a CISO and in IT management for a long time and always been frustrated by how much waste I&#x27;d find in every environment - idle EC2 instances running 24&#x2F;7, oversized RDS databases, forgotten storage volumes, test resources that never gets removed. What also bothered me was that nobody was tracking the environmental cost of this waste. Every unused resource burns electricity and contributes to carbon emissions unnecessarily.<p>What it does:<p>- Scans AWS accounts using IAM roles or access keys, GCP projects using service account keys<p>- Identifies specific optimization opportunities: unused EC2&#x2F;Compute Engine instances, oversized databases, unattached storage, missed reservation opportunities and much more<p>- Calculates financial savings AND CO₂ reduction for each recommendation using region-specific grid emission factors<p>- Multi-account&#x2F;project support<p>- Generates detailed reports with prioritized recommendations<p>Technical details: Built with React&#x2F;TypeScript frontend, Supabase backend. Uses AWS SDK for EC2, RDS, Cost Explorer APIs and GCP&#x27;s Compute Engine, Cloud SQL, and Cloud Billing APIs. Carbon calculations combine cloud provider PUE data with regional electricity grid emission factors from government sources.<p>Try it out: The onboarding from creation to your first scan being run is only ~30 seconds. The scanning process is fully automated and typically completes in 5-30 minutes depending on account size of course.<p>I would genuinely love to get your feedback on it, just came out of beta a few days ago so if there&#x27;s any bugs around please do let me know =)<p>If you&#x27;re on Linkedin let&#x27;s connect: <a href="https:&#x2F;&#x2F;www.linkedin.com&#x2F;in&#x2F;almstedt&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.linkedin.com&#x2F;in&#x2F;almstedt&#x2F;</a><p>Sources:<p>&quot;companies estimate that 21-50% of their cloud expenditure is wasted&quot; (<a href="https:&#x2F;&#x2F;www.techmonitor.ai&#x2F;hardware&#x2F;cloud&#x2F;cloud-waste-hits-billions-as-78-of-firms-report-significant-expenditure-losses" rel="nofollow">https:&#x2F;&#x2F;www.techmonitor.ai&#x2F;hardware&#x2F;cloud&#x2F;cloud-waste-hits-b...</a>)<p>&quot;45% of cloud customer’s expenditures are spent on resources they will never use&quot; (<a href="https:&#x2F;&#x2F;www.sciencedirect.com&#x2F;science&#x2F;article&#x2F;abs&#x2F;pii&#x2F;S2210537922000476" rel="nofollow">https:&#x2F;&#x2F;www.sciencedirect.com&#x2F;science&#x2F;article&#x2F;abs&#x2F;pii&#x2F;S22105...</a>)<p>&quot;21% of enterprise cloud infrastructure spend &#x2F;.. &#x2F; in 2025*—is wasted on underutilized resources (<a href="https:&#x2F;&#x2F;www.prnewswire.com&#x2F;news-releases&#x2F;44-5-billion-in-infrastructure-cloud-waste-projected-for-2025-due-to-finops-and-developer-disconnect-finds-finops-in-focus-report-from-harness-302385580.html" rel="nofollow">https:&#x2F;&#x2F;www.prnewswire.com&#x2F;news-releases&#x2F;44-5-billion-in-inf...</a>)

[Testing] Go Assembly Mutation Testing

[Other] Show HN: Astro dev blog template with interactive colorschemes I&#x27;ve created and open-sourced an Astro developer blog template with an interactive theme changer that includes all 60 themes bundled with the JS code highlighter Shiki. Changing the theme affects the whole website including the code examples and Giscus comments. Inspired by the aesthetics of raw markdown, I wanted to create a beautiful blog like <a href="https:&#x2F;&#x2F;github.com&#x2F;panr&#x2F;hugo-theme-terminal">https:&#x2F;&#x2F;github.com&#x2F;panr&#x2F;hugo-theme-terminal</a> but supercharged with a modern redesign and the incredible features of Astro.<p>Features:<p><pre><code> - Simple configuration file - Multiple theme modes (single, light&#x2F;dark&#x2F;auto, select) - Giscus comments - RSS feed - SEO best practices + social card generation - Markdown extensions (TOC, admonitions, reading time, etc)</code></pre>

[API/SDK] Show HN: Mcp-use – Connect any LLM to any MCP Hey Pietro and Luigi here, we are the authors of mcp-use (<a href="https:&#x2F;&#x2F;github.com&#x2F;mcp-use&#x2F;mcp-use">https:&#x2F;&#x2F;github.com&#x2F;mcp-use&#x2F;mcp-use</a>).<p>When the first MCP servers came out we were very excited about the technology, but as soon as we wanted to get our hands dirty, we found out that MCP could be used only through Claude Desktop or Cursor. As engineers, we did not like that. MCP seemed like something you wanted to use to build products and applications yourself, not something to hide behind a closed source application.<p>So we approached the SDK but were pretty dissatisfied with the developer experience (double async loops, lots of boilerplate). We decided to write mcp-use to make our lives easier.<p>mcp-use lets you connect any LLM to any MCP server in just 6 lines of code. We provide a high level abstraction over the official MCP SDK that makes your life easier and supports all the functionalities of the protocol.<p>Demo video here: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=nL_B6LZAsp4" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=nL_B6LZAsp4</a>.<p>The key abstractions we provide are called MCPClient and MCPAgent.<p>MCPClient takes in a set of server configurations, automatically detects the transport type and creates a background task which handles the stream from&#x2F;to the server.<p>MCPAgent is a combination of the MCPClient, an LLM, and a custom system prompt. It consumes the MCP client by transforming the tools, resources and prompts into model agnostic tools that can be called by the LLM.<p>The library also contains some cool utilities:<p>- secure sandboxed execution of MCP servers (we know the protocol doesn&#x27;t shine for security)<p>- meta-tools that allow the agent to search over available servers and tools (to avoid context flooding) and connect dynamically to the server it needs (you could create the omnipotent agent with this).<p>Some cool things we did with this: - write an agent that can use a browser and create&#x2F;read linear tickets updated with latest information on the internet<p>- write an agent that has access to the metrics of our company to automatically create weekly reports.<p>- I connected an agent to an IKEA curtain I hacked an MCP on to adapt the lighting of my room from images of the lighting situation.<p>- recreated am open source claude code like CLI, with full MCP capability but with custom models and BYOK (<a href="https:&#x2F;&#x2F;github.com&#x2F;mcp-use&#x2F;mcp-use-cli">https:&#x2F;&#x2F;github.com&#x2F;mcp-use&#x2F;mcp-use-cli</a>).<p>We recently crossed 100,000 download and we are used by many organizations, including NASA!<p>We’d love to hear what you think of it, most importantly how we can improve it! We are happy to answer any questions and look forward to your comments.

[API/SDK] Show HN: AgentMail – Email infra for AI agents Hey HN, we&#x27;re Haakam, Michael, and Adi. We&#x27;re building AgentMail (<a href="https:&#x2F;&#x2F;agentmail.to&#x2F;">https:&#x2F;&#x2F;agentmail.to&#x2F;</a>), an API to give AI agents their own email inboxes. We’re not talking about AI for your email, this is email for your AI.<p>We started building email agents because they can converse with users in their inboxes, automate email-based workflows, and authenticate with third-party applications. Given these unique capabilities, we think email will be a core interface for agents.<p>But we were building on top of Gmail, which was a struggle: poor API support, expensive subscriptions, rate limits, sending limits, GCP Pub&#x2F;Sub, OAuth, crappy keyword search, and an overall terrible developer experience.<p>Gmail and other providers didn’t work for us. So we decided to bite the bullet and build our own.<p>AgentMail is like Gmail, but API-first, with programmatic inbox creation, events over webhooks and websockets, simple API key auth, organization-wide semantic search, structured data extraction, and usage-based pricing that scales with emails sent&#x2F;received.<p>Here’s a demo of building an email agent: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;1V7BISeFUTM" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;1V7BISeFUTM</a>, and here’s a demo of a voice agent with its own email inbox: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;eG2fCsRK4RY" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;eG2fCsRK4RY</a><p>So far AgentMail has been deployed to use cases such as apps with dedicated inboxes for each user, voice agents that receive documents in real time, automated account provisioning and QA testing, cold outbound platforms with thousands of inboxes, automations for processing invoices, and agents that coordinate work with humans and other agents.<p>We would love to hear your thoughts and feedback. You can try our playground at <a href="https:&#x2F;&#x2F;chat.agentmail.to">https:&#x2F;&#x2F;chat.agentmail.to</a>

[Other] Ongoing Lean formalisation of the proof of Fermat's Last Theorem <a href="https:&#x2F;&#x2F;github.com&#x2F;ImperialCollegeLondon&#x2F;FLT&#x2F;blob&#x2F;main&#x2F;GENERAL.md">https:&#x2F;&#x2F;github.com&#x2F;ImperialCollegeLondon&#x2F;FLT&#x2F;blob&#x2F;main&#x2F;GENER...</a>

[Database] GenosDB (GDB) – Decentralized P2P Graph Database