ShivGuruTattva — NirgunaShunya

What it does

An ultra-lean ~291KB local middleware wrapper enforcing absolute post-quantum security and alignment for autonomous AI Agents at the execution layer. 100% network independent with zero outbound dependencies. Built on a <10KB axiomatic logic core, the engine features a certified 100% mitigation rate across 18,081 adversarial vectors, including 2,412 prompt injections and 3,156 semantic drifts. Test the live validation array firsthand via our website-integrated Replit sandbox.

NirgunaShunya is India

• 
  CtrlAIMar 2026 · ▲104

  Transparent proxy that secures AI agents with guardrails

• 
  AegisoraAug 2026 · aegisora-ai.vercel.app · ▲93

  The narrow control plane for AI agent tool and API calls.

• WI
  We instrumented Claude Agent SDK using a tiny Rust proxyDec 2025 · laminar.sh · ▲6

  At Laminar (https:&#x2F;&#x2F;github.com&#x2F;lmnr-ai&#x2F;lmnr) we're building open source AI observability platform in Rust. We obsess over instrumentation DX for our Python and TS SDKs and in this new blog we outline how we made the most seamless way of instrumenting recently released claude agent sdk

• AA
  Agent Armor, a Rust runtime for enforcing policies on AI agent actionsApr 2026 · github.com · ▲7
• RV
  Retroguard – Verifiably secure AI guardrailsMay 2026 · retroguard.ai · ▲6

  Cryptographically secure and verifiably robust protection with drop-in integration and outcome-based pricing

• CA
  CLRK, an open-source agent runtime with gVisor and MitM guardrailsJul 2026 · github.com · ▲5

  TL;DR: we built a framework-agnostic agent runtime that uses gVisor for isolation and runs on k8s. It’s open-source under AGPLv3 Recently we’ve been working on a customer support “AI assistant” - essentially an interactive knowledge base&#x2F;L1 support but with an option to touch resources that belong to a customer it’s talking to. We found existing tools to be lacking in these aspects: 1. Fully intercepted i&#x2F;o. We wanted to trace out LLM calls as well as any other networking calls attempted by the harness so that guardrails and audit trails apply to all current and future systems…

• 
  I trained a 125M model to autocomplete piano on-device▲598

  I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes&#x2F;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▲585

  Automate your B2B brand going viral, with new media creators

  AI · 18d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 25d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  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&#x2F;sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens&#x2F;sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

  AI · 27d ago · cactuscompute.com

• 
  Coldtea.ai▲512

  Make your software self-driving

  AI · 30d ago · coldtea.ai

• 
  Soloop▲472

  Approval-first Agent OS for solo founders

  AI · 30d ago · soloop.io

• TL
  The load-bearing vocabulary of Claude▲703

  Life & fun · 10d ago · louisabraham.github.io

• 
  Hey Noah▲641

  A proactive AI executive assistant for founders

  AI · Aug 2026 · heynoah.io

• 
  Clipto MCP▲640

  Let agents source clips from terabytes of your local video

  Work · 18d ago · clipto.com

• SA
  Simple algorithm and color space to generate diverse skin tones▲627

  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

• 
  AdAnt AI▲608

  Claude for viral, high-converting social ads

  AI · Aug 2026 · adant.ai

• 
  I trained a 125M model to autocomplete piano on-device▲598

  I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes&#x2F;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