Opensourcing APH Engine and Servers in Rust and N Lang
rustaceans, we've completely open sourced our APH rust engine and servers! APH is a Agent Per Human notarization protocol, that acts like remote guardrails for when your agents are working with agents you don't own. It allows both parties to share public keys that they can verify each other are working in good faith against public servers. APH by Squillo is the missing piece of the A2A and AP2 families from Google, built with the same pedigree as the web but for the agentic web. It's designed to work with existing agentic protocols and future ones, but is the cornerstone for the agentic web…
What it does
APH - Agent per Human Notarization Protocol. Contribute to squillo/aph development by creating an account on GitHub.
In the maker’s words, at launch
rustaceans, we've completely open sourced our APH rust engine and servers! APH is a Agent Per Human notarization protocol, that acts like remote guardrails for when your agents are working with agents you don't own. It allows both parties to share public keys that they can verify each other are working in good faith against public servers. APH by Squillo is the missing piece of the A2A and AP2 families from Google, built with the same pedigree as the web but for the agentic web. It's designed to work with existing agentic protocols and future ones, but is the cornerstone for the agentic web and true agentic commerce. Now, get blistering speed, memory safety, and security for you and your Agents. Don't do rust? no worries, it's ready to go with wasm/wasi and we've installed a claude and codec packs to make it easy to implement. Now, an agent can responsibly bid on eBay, negotiate your medical bills, buy a house, trade on the stock market, all with the remote guardrails you can independently verify without leaking secrets.
Does the same job
all alternatives →
Remote OpenClawJul 2026 · codexmarketplaces.com · ▲8113,000+ MCP servers, skills & plugins for AI coding agents
Aura – a Rust agent that investigates and fixes production incidents4d ago · github.com · ▲25AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure. - mezmo/aura
- ODOrch8 – Durable workflow engine in Rust, one binary, Postgres or SQLiteMay 2026 · github.com · ▲26
- DODocs over SSH for AgentsApr 2026 · github.com · ▲9
Coding agents spend a lot of time in the shell. When exploring a codebase, they usually reach for the same handful of tools: grep, find, ls, cat. We built a public SSH server that hosts Supabase docs as markdown files so that agents can explore them the same way they explore code: ssh supabase.sh grep -rl 'RLS' docs ssh supabase.sh cat docs/guides/database/postgres/row-level-security.md | head -10 Under the hood commands run inside Vercel's just-bash [1] library - an emulated bash shell sandboxed within the JS runtime. It uses a VFS where the docs are mounted as markdown…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com