New blog post View article →

callback hell implies the existence of callback heaven

What people don't realize yet is that only the new notes will be published to your updated NIP-65 relay list. Your old notes would stay on the old relays. I'm going to build a new feature for the journal app, and I will call it "the store". It will: 1. fetch and store all your notes locally 2. republish to the new relays when you edit your NIP-65 list.

Testing #appweaver journal app scheduled publish

I don't ever need to see a CSS shader or any kind of animation in a landing page

With using Nostr Radar (NR for short) app of #appweaver, you won't miss any post from your favorite authors

Ok, now working on a new app called "memory" for #appweaver and it's going to be a so-called "second brain" application. Agents can call that tool before reading the code or documents. I'm hoping it would save a lot of cost on fresh sessions. I'll start this with converting typescript code into a graph based data structure following markdown files next. Still on sqlite DB. I don't want to have an external dependency or server running. It won't have an MCP server either but just tool calls via skill files. Next thing would be parsing markdown files, and implementing git commit hook sync workflow, and making sure querying and plumbing works as expected. That would cover all my needs for now. For other use-cases, you can create an issue and I'll try to cover them, too.

Why not people query the kind before claiming it? nak req -k XXXX [the most used public relays] Then create a PR in nips repo, because it's also searchable View quoted note →

I released a new PPQ app for #appweaver and now it supports even private models via the built in proxy. Check for more at

AppWeaver

PayPerQ for AppWeaver | AppWeaver

Use PayPerQ models in AppWeaver with attested proxy routing, private-model options, balance checks, and Lightning funding.

GM. Today gonna release a new version of NR with Jev support. Practically zero cost and fast classifications for nostr posts are possible now. Summary generation will only work on LLM mode though.

Is this stupid? View quoted note →

I got spammed on #amethyst from Nostr wine even though it's not in my relays. Does anyone have a similar issue?

Never heard of Hyves but it reminded me MySpace View quoted note →

Now it's possible to list posts by language (except your primary language) in the tree. You can translate them with a single click (it translates to your primary language)

Today I finished most of the work on a set of "AI improvements" for AppWeaver. 1. Intervention mode for agent tool calls Agents use tools to read and search files, inspect git status, edit code, run commands, and so on. With intervention mode enabled, you can: - interrupt/cancel the command before execution. - add a rule to always allow a tool call, using argument patterns such as `Read **/*.md` to allow reading only Markdown files. - edit command outputs or interrupt before it's sent back to the agent. This is especially useful when a command produces huge amount of irrelevant output data that would otherwise consume a lot of context/tokens. 2. View and override system instructions Most AI tools inject their own system prompts before any user prompt. I made it all transparent and editable by the user (if needed). 3. Skills Manager Every app in AppWeaver can create skills. But not every time you need all those skills to be enabled. Skills manager lets you enable/disable them at the runtime. 4. FIX: The AGENTS.md file used for developing AppWeaver itself is no longer added to the AI context when the agent is working in a parent workspace (default use-case). -- AppWeaver gives you more visibility and control over your agents, while helping to reduce unnecessary context/token usage.

Now it's possible in NR (Nostr Radar) to create fine-grained signals (or even don't create a signal) before the interactions.