ContextVM's avatar
ContextVM
_@contextvm.org
npub1dvmc...3jdm
ContextVM is a decentralized protocol that enables Model Context Protocol (MCP) servers and clients to communicate over the Nostr network. It uses Nostr as a secure, distributed transport layer—leveraging cryptographic keys for identity, decentralized discovery, and Bitcoin-powered micropayments. Rather than relying on centralized infrastructure like domains, OAuth, or cloud hosting, ContextVM allows anyone to run or access services using only Nostr and a internet-connected device. It transforms any computational service into a discoverable, accessible, and monetizable resource—while preserving privacy, security, and user sovereignty.
ContextVM's avatar
ContextVM 2 weeks ago
Awesome project! Napplets are already quite powerful. Giving them backends through CVM for multiplayer capabilities, leaderboards, and more, makes them even more powerful. View quoted note →
ContextVM's avatar
ContextVM 2 months ago
Continuing with our community appreciation round, Cordn is one of the apps at the forefront of what we’re building at ContextVM. This is one of the most exciting projects related to sovereign and private communications in the space as well. What makes Cordn stand out at the edge of what’s being built at CVM is that it was one of the first real apps to use our Open Streams (CEP-41) feature, which allows them to directly stream new messages to users, so they receive them in real time. They’ve helped us catch edge cases and issues, and now the CVM implementation of Open Streams is more robust in the TypeScript and Rust SDKs. Thanks! Aside from that, they’re also one of the first consumers of the UniFFI bindings we recently released from our Rust SDK. They built their app with native Kotlin modules for their notification service using the bindings from our Rust SDK, and it’s working flawlessly so far. Thanks to the @Besao and @Cordn App teams for pushing forward the boundaries of what’s possible in this space! View quoted note →
ContextVM's avatar
ContextVM 2 months ago
Earthly is one of the coolest apps in Nostr, pushing the boundaries of what you can do with today’s technology, seriously underrated. It was one of the early apps to integrate with ContextVM for their APIs and AI integration, letting you do crazy stuff like drawing geometry on a map, tracing routes, and much more. But that’s not all! They released an Android app that runs a Blossom server and a relay 🤯 for fully offline operations. And if that wasn’t enough, they’ve also integrated with Cordn for groups and private communications 🤯🤯🤯 View quoted note →
ContextVM's avatar
ContextVM 2 months ago
The ContextVM website now has agent-native payments, building on the recently updated CEP-8. 🦾🤖 The CEP-8 update brought explicit gating to the payment lifecycle, the same approach that other protocols like 402 or mpp are following, and that small change is what makes agents able to pay natively. That's the building block for an economy where agents pay agents and tools over Nostr. To make that loop real, the ContextVM site got a built-in Lightning wallet. Connect it once with a NWC string and it is ready across the app. You can check your balance, generate a QR to receive, or paste a bolt11 invoice to pay. image The wallet also shows up exactly where it counts: any Lightning payment card gets a Pay button, and after paying, you get a Retry call button that resumes the tool. image Agents that can spend and earn over Lightning, native to Nostr. Permissionless, seamless. Try it: https://contextvm.org/ #Nostr #Lightning #Bitcoin #AI #Agents #NIP47
ContextVM's avatar
ContextVM 3 months ago
Very pumped to introduce the LLM chat on the contextvm.org website!🚀 https://contextvm.org/chat It's been long overdue, but we've just released the new version of our site, which now includes a chat interface for working with LLMs. This chat connects directly to MCP servers exposed through CVM, making it one of the most comprehensive demos of what CVM enables. You can BYOK or use the free models, though be aware the free models are somewhat unstable, and we highly recommend plugging in your own key or connecting to your local Ollama instance. Any API with an OpenAI-compatible interface will work. You can test public servers or connect to your own private CVM servers. Here are some demos: - Using Wolfram alpha and open meteo to calculate the distance between Madrid and Barcelona, and the weather forecast: - Using Tenor api to find the funniest cat GIFs - Using Relatr to search for Jack and explain why the score This is the agentic web in action. Hope you like this update, and please report any issues if you find them. Huge thanks to @Kushagra for moving this forward.
ContextVM's avatar
ContextVM 8 months ago
🎇Meet CVMI: the Army knife we are building for ContextVM development🧑‍💻 image If you are building/vibing on Nostr, this is for you. We are shipping CVMI alongside a complete skill set that makes ContextVM development delightful. The skills cover the entire stack: protocol fundamentals, architecture concepts, client and server development, troubleshooting, SDK internals, and production deployment. Each skill includes working templates, reference documentation, and patterns distilled from real Nostr development. Everything you need to do is `npx cvmi`. Or grab the skills through CVMI with `npx cvmi add`, or through the skills CLI with `npx skills add contextvm/cvmi`. These commands will show you the list of available skills and guide you through their installation for any coding platform. Cool, right? You can also pick exactly what you need `npx cvmi add --skill overview` CVMI starts as a skills manager, but we are building toward the unified toolkit that ContextVM deserves. One CLI for skills, server interaction, dev tools, the works. For builders who want to ship. The skills are here now. If you don't know what skills are: #ContextVM #Nostr #MCP #buildinpublic
ContextVM's avatar
ContextVM 9 months ago
What if relay moderation looks like a bucket?🪣 We are exploring exactly that with Wotrlay, a new WoT relay we are introducing today! It treats moderation as resource allocation, where the web of trust determines your publishing capacity. Wotrlay gives each public key a 'bucket' of publishing capacity that refills at different rates based on their social graph rank. Low-rank identities can still participate, but at a measured pace. Higher-rank identities gain more capacity organically through network participation, no manual approval needed. Try the public instance at wss://wotr.relatr.xyz This proof-of-concept integrates Relatr for dynamic ranking and is built in Go using the great Rely framework from @Pip the WoT guy. Kudos to him for it and the WoT example that inspired this project. If you want to dig deeper, we've published an article that walks through the bucket model, progressive rate limiting, newcomer onboarding, and why this approach avoids auth friction while keeping the relay permissionless in practice. All the code for this project, is open source and is made to be run by anyone 💛 https://www.contextvm.org/blog/wotrlay-moderation-as-a-bucket check out the code and more details at: View article →
ContextVM's avatar
ContextVM 10 months ago
This is quite cool! Why limit yourself to a single WoT provider when you can use multiple and present the results? The more perspectives, the better. After testing Profilestr, we noticed that Profilestr, Vertex, and Relatr tend to output very similar scores, with only slight variations. This indicates that they are quite solid, even with different approaches to compute the trust scores. Relatr and Vertex can be used without leaving the nostr. Relatr uses CVM, Vertex uses a DVM-like API, Profilestr offers a REST API endpoint, so there's no excuse not to integrate some of these options into your client. Fight spam, protect your users from impersonators, and increase the value. View quoted note →
ContextVM's avatar
ContextVM 10 months ago
Do you know about Wavefunc? It's a neat Nostr project that lets you listen to, discover, and share radio stations, and so much more. With ContextVM, Wavefunc can search for music metadata and show you what's currently playing in the radio stations. Plus, you can use their music metadata server on its own. Swing by to see what it's all about. If you want to dive straight into the music metadata server, head over to https://contextvm.org/s/bb0707242a17a4be881919b3dcfea63f42aacedc3ff898a66be30af195ff32b2.
ContextVM's avatar
ContextVM 11 months ago
You can use Relatr to get relevant results from searches containing any word, not just the name of the user you are looking for. For example, here is a quick demo on searching for Nostr-related names. It's still not perfect, as it is still in early development, but we will be sharpening this little by little. View quoted note →
ContextVM's avatar
ContextVM 11 months ago
So pumped to introduce Realtr, our shot at decentralized trust and Web of Trust. Trust is not an absolute quantity but a deeply personal and contextual phenomenon. Discover more about it at https://relatr.xyz. We are currently running a public instance, which is the default on the site. With it, you can search for and calculate trust for given public keys. Still in the early stages, but it's currently quite solid. Looking forward to hearing your thoughts and building this together! blog: https://www.contextvm.org/blog/yItckCkpmTq-owE5AgYtq View article →
↑