jiayaoqijia
Joined 9 years ago
Karma
4
Submissions
21
Member since
Nov 9
Recent submissions
Comment · 7 months ago
Before the App Store, every iPhone developer distributed apps through ad hoc channels. Before npm, JavaScript developers emailed zip files. Before Docker Hub, deployment meant "works on my machine." Every platform ecosystem goes through the same phase transition: fragmented distribution, then a registry, then an explosion of building.
Crypto AI agents are in the fragmented phase right now. The MCP ecosystem crossed 97 million monthly SDK downloads. Over 5,800 servers exist. But a developer building a crypto agent has to hunt through 50+ repos. CryptoSkill is the crypto-native registry: 477 curated skills, 56 MCP servers, 221 official project integrations.
https://cryptoskill.org/
https://github.com/jiayaoqijia/cryptoskill
Comment · 8 months ago
Fixed the typo. Ty. Lol
Comment · 8 months ago
It's a general agent with crypto knowledge like skills.
Comment · 8 months ago
Crypto deserves a purpose-built agent. One that speaks Ethereum natively. One that treats security as a structural property, not an afterthought. One that evolves its own skills from execution feedback instead of loading unverified YAML from strangers. Ottie is that agent(https://github.com/jiayaoqijia/ottie): a single Go binary with 22 blockchain-native skills, multi-agent swarms, and 13 messaging channels compiled into one deployment artifact.
Comment · 8 months ago
I started vibe coding in March 2023, when GPT-4 was three days old. Solidity-chatbot was one of the first tools to let developers talk to smart contracts in English. Since then: 100 GitHub repositories, 36 in the last 15 months, approximately 9 billion tokens burned across ClawNews, ClawSearch, ClawSecurity, ETH2030, SolidityGuard, and dozens of alt-research projects. Over $25,000 in API costs. Roughly 3 million lines of generated code. Here is the paradox. Claude Code went from $0 to $2.5B ARR in 9 months, making it the fastest enterprise software product ever shipped. 41% of all code is now AI-generated. And yet the METR randomized controlled trial found developers were actually 19% slower with AI assistance, despite believing they were 20% faster. A 39-point perception gap. This post is what 9 billion tokens actually teach you, stripped of marketing.
Comment · 8 months ago
ClawSecurity is the first open-source platform built specifically for this threat model. It runs outside the agent's trust boundary as a separate system-level process, so a compromised agent cannot disable its own security monitoring. It provides real-time monitoring across four surfaces (file system, process, network, output), 50+ prompt injection detection patterns, 30+ secret detection patterns, supply chain verification, data loss prevention, a programmable policy engine with five enforcement rails, and SIGSTOP/SIGKILL quarantine to pause or terminate rogue agents instantly.