K.Crafter retweetledi
a lot of people don't know about the tech behind Spark yet, and I couldn't do a good job of this either
between TGE & and all the stuff
Here is what Spark is in a nutshell:
1. It's a self-improving personal agent
2. Most similar thing to it is Hermes agent but Hermes focuses on creating skills from your work, while Spark is a recursive agent that can create benchmarks, self-improvement loops, and train even while you sleep.
3. It has memory, canvas, kanban, skill-pairing nodes, progress reports directly relayed to telegram agent while building and a lot more useful stuff.
4. I've been building it with insane amounts of inference, since 4 months, often 10+ terminals open to get it right
5. While building it, my GitHub probably became the most committed GitHub in the whole blockchain community, that much work put into it.
6. It is live, and you can already start using it. FYI, I need a lot of user data and PRs, because this is an agent harness and till now I've been building it solo. You can access it at agent.sparkswarm.ai
7. For that there is compete.sparkswarm.ai that you can join to send PRs, 1.5% of supply is dedicated to this first event, called Hunting Bugs & Goblins.
8. Personal agents are the second biggest thing after frontier AI labs, and Spark is about building an ecosystem around it too via grants, hackathons and incubations, so that we can bring a new breed of an agentic ecosystem at the core of a self-improving personal agent.
9. Also, if you hold Spark you will get free tokens from all these projects that enter our ecosystem through grants, hackathons and incubations.
10. Spark is quite friendly with blockchain seeing the benefits this tech-stack can bring to agentic funding, transactions, and ecosystem building, instead of being against it.
Let's call it our homegrown personal agent. Still there is a lot to build on, and it is just the beginning of the journey, except the product is at a state where once polished it will be able to compete with the best.
As what's inherent in it, is how frontier AI labs train the best models. Recursive loops tied to a personal agent.
English
