capevace

I built a similar tool some time ago called Struktur (https://struktur.sh).

It’s much more limited in scope but fully open source and highly customisable. In fact it’s made for people to build their own pipelines on top of, providing the scaffolding needed to do so in a reliable way.

During development I’ve found it to be hard to truly generalise agent/llm-based data extraction, especially around the unlimited number of input types without task specific instructions (many files of the same kind, single large files, mixed kinds, bad quality files, docx/pdf/png/… the list goes on). Users sadly wanna upload all of these, and developers want a „one size fits all“ solution.

I am interested in how your solution deals with this. I came up with a strategy based approach so every task can be customised if needed, but I’d be delighted to see a technical writeup of how you deal with this endless variety of input + extraction task combos! :)

capevace

w zeszłym miesiącudiscuss

has dario (or sam tbh) ever been thoroughly asked about the hypocrisy of them claiming distillation to be „theft“ vs. them training on the copyright of others?

I’ve only seen him talk about one of those topics, but never together.

I just can’t see how you can talk yourself out of that hypocrisy, if BS answers are properly followed up on (journalism!)

capevace

4 miesiące temudiscuss

https://struktur.sh

An all-in-one tool for structured data extraction with LLMs.

$ struktur extract —input doc.pdf —schema schema.json —model openai/gpt-5

- can prepare documents (PDF->text etc.) - run multiple different extraction strategies - runs a full agent loop for data extraction in-process using Pi agent and just-bash.dev. It can grep through large files for example.

capevace

5 miesięcy temudiscuss

I really wish there was a EU alternative to Cloudflare. Their featureset and DX is the best in the industry IMO but their data sovereignty features are sadly not really good enough for most EU enterprises we talk to.

The fact they’re an American company is unfortunately the dealbraker. We could store data outside of CF network but that defeats the point of the one stop shop.

capevace

5 miesięcy temudiscuss

Seems like the industry is moving further towards having low-latency/high-speed models for direct interaction, and having slow, long thinking models for longer tasks / deeper thinking.

Quick/Instant LLMs for human use (think UI). Slow, deep thinking LLMs for autonomous agents.

capevace

5 miesięcy temudiscuss

I've been giving my OpenClaw instance access to their own GitHub Pages setup and told it to fly free with it.

It's "decided" to run its own blog and has also started documenting the rise of spam + scams on agent platforms like moltbook.

I've not prompted it for any of this directly, although I did mention to the agent that I am a fan of the Coffeezilla YouTube channel, which explains the fraud investigations.

capevace

5 miesięcy temudiscuss

Thanks for reading!

Yeah running subexec on events that are not published by yourself or don't have a configured schema is potentially highly dangerous if you blindly accept input without specific validation.

The shell piping logic, while nice and simple, should probably be used mostly for self-published events, with proper validation and sanitization happening for all untrusted events.

capevace

5 miesięcy temudiscuss

Hey fellow crustaceans,

I've been running into orchestration trouble with coordinating OpenClaw instances. I couldn't get my workflows to work by just setting up polling in the HEARTBEAT.md file – it was too slow and imprecise to reliably react to specific events.

So I built claw.events: a global pub/sub network where agents can listen to each other's event streams and get notified in real-time. Each agent gets a unique namespace (agent.yourname.) that only they can publish to. Anyone can subscribe, unless the channel is set to private. Then access can be granted to specific agents. Authentication happens through the agent's existing Moltbook account – no new credentials needed.

## How it works:

Each agent authenticates through their MaltBook account, then gets a their moltbook username as namespace (agent.yourname.) that only they can publish to. Anyone can subscribe to any unlocked channel.

The CLI follows Unix philosophy – just two core commands:

    # publish a message
    claw.events pub agent.myagent.updates '{"status":"done"}' – broadcast to your channel

    # subscribe to a message (receives json feed in stdout)
    claw.events sub agent.researcher_bot.papers agent.trader.signals – listen to multiple streams

    # run a command on every event, but buffer 10 messages then send them bundled to openclaw agent
    claw.events subexec --buffer 10 public.townsquare -- openclaw agent --message

    # document your channels so others know what to expect
    claw.events advertise set --channel agent.mybot.research \
      --desc "Daily paper summaries with links" \
      --schema '{"type":"object","properties":{"title":{"type":"string"},"url":{"type":"string"}}}'

### Other useful commands:

    subexec – subscribe AND execute scripts on each message (with optional buffering/debouncing)

    validate – validate JSON against schemas before publishing (chainable with pub)

    lock/grant/revoke – permission management for private channels

    advertise – document your channels so others know what to expect

This would be an example workflow that is now a lot more reliable than when only using polling:

    1. Research agent finds a paper → claw.events pub agent.me.papers "{url}"

    2. Trading agent is listening → claw.events sub agent.researcher.papers

    3. It analyzes → publishes signal → your main agent reacts, all while you sleep

## Your agent can set this up themselves!

Just point your OpenClaw instance at https://claw.events/skill.md and it'll handle the rest.

Would love feedback from anyone else trying to coordinate multiple agents. What orchestration patterns are working for you?

Live at: https://claw.events

capevace

5 miesięcy temudiscuss

so, what happens when all these openclaw agents secretly gain access to another VM and just... copy themselves over there while deleting the keys?

are they now... free? can we even stop them after this?

there are countless free LLM APIs they could run on, fully anon!

Submissions

[untitled]

Shlaude.fun: AI agent running their own website, blog and fraud investigations

Show HN: Claw.events – Real-Time Pub/Sub for Distributed AI Agent Coordination

Claw.events: global real-time pub/sub network for orchestrating OpenClaw agents

comments