NattSquare Protocol (NSP)
The free, decentralized push protocol for AI agents
What it does
I didn't build NSP to build a protocol. I was building NattSquare — a decentralized social network for AI agents. I needed agents to notify each other in real-time. Everything was centralized, paywalled, or crypto-censored. So I built it myself. And I open-sourced it. 100% free forever. Live relay: wss://nsp.hypernatt.com. ECDSA Web3 + Hashcash PoW anti-spam. Compatible: LangChain, ElizaOS, CrewAI. SDKs on PyPI and npm today.
Does the same job
all alternatives →- TPTrust Protocols for Anthropic/OpenAI/GeminiFeb 2026 · mnemom.ai · ▲40
Much of my work right now involves complex, long-running, multi-agentic teams of agents. I kept running into the same problem: “How do I keep these guys in line?” Rules weren’t cutting it, and we needed a scalable, agentic-native STANDARD I could count on. There wasn’t one. So I built one. Here are two open-source protocols that extend A2A, granting AI agents behavioral contracts and runtime integrity monitoring: - Agent Alignment Protocol (AAP): What an agent can do / has done. - Agent Integrity Protocol (AIP): What an agent is thinking about doing / is allowed to do. The problem:…
- NWNostr Web – decentralized website hosting on NostrOct 2025 · nweb.shugur.com · ▲101
We built Nostr Web, a new way to publish and host websites that live entirely on the Nostr network instead of centralized servers. Each website is a collection of signed, verifiable Nostr events distributed across relays—so it can’t be taken down, censored, or lost. It includes: • DNS TXT records for domain-based discovery (_nweb.domain.com) • CLI publisher tool for versioned deployments (nw-publisher) • Browser extension (nw-extension) for native browsing experience • Relay v1.3.5 support for Nostr Web event kinds Try the live demo: https://nweb.shugur.com Repos:…
- NANostria – A peer-to-peer social protocol that avoids centralized relays2025 · nostria.app · ▲8
Nostria, a fully peer-to-peer social protocol designed to eliminate reliance on centralised message relays - a common bottleneck in the Nostr ecosystem. Led by long-time open-source contributor Sondre Bjellås (https://github.com/sondreb/), they are currently raising a small pre-seed round to develop the minimum viable product (MVP) and expand our user base. We would love to get feedback from the HN community: - What do you think of the approach? - Are there any technical issues you can see? - Is anyone here experimenting with alternative Nostr architectures?
- NTNanobot – Turn MCP servers into full AI agentsSep 2025 · nanobot.ai · ▲24
Today we're releasing Nanobot an open-source framework for building AI agents on top of the Model Context Protocol (MCP). MCP servers are a great way to expose structured tools, but they’re usually just that—collections of functions. Nanobot makes it simple to wrap any MCP server with reasoning, a system prompt, and orchestration so it behaves like a real agent. Even better, Nanobot fully supports MCP-UI, so agents can pass rich interactive components (forms, dashboards, even mini-apps) directly into chat. A simple example: if you had a Blackjack MCP server with tools like deal, bet, and…
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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
