Daize Dong DaizeDong
Highlights
- Pro
Organizations
@RAISL-CoreStars
A living, execution-graded coding-agent benchmark (false_accept=0): tasks mined from real merged PRs daily, models scored only by re-laid protected tests.
High-accuracy skill activation (88%+) for Claude Code with AI-analyzed keywords, weighted scoring, synonym expansion, and three-tier confidence routing
Automate multi-channel product promotion (email/posts/forum/DM), track conversion funnel, self-tune via feedback.
Methodology skill + deterministic harness for agents that self-iterate any skill/repo/project. Anti-self-deception by design — an un-gameable acceptance gate so 'accepted = real improvement', not a...
Thin orchestration Claude skill for consumer shopping price comparison — Amazon / eBay / Walmart / Target / Taobao / JD + price-history (Keepa / Camelcamelcamel / 慢慢买) + coupon stacks (Capital One ...
A Pi Pilot Tool for Researchers, Graduate Students, and Myself...
Thin Claude Code skill for commercial/market research. Triages 15 specialized data domains, detects + auto-configures the right MCP sources, delegates heavy retrieval to deep-research. Curated sour...
Framework for evaluating and improving agents
A benchmark for LLMs on complicated tasks in the terminal
LLMRouter: An Open-Source Library for LLM Routing
A lightweight gallery of mathematical curve based loading animations with modal previews, formulas, and copyable code snippets.
A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC. A delectab...
Claude Code plugin: end-to-end used car buying — multi-site research, mass dealer outreach, OTD negotiation with 50-state fee data, CARFAX analysis, decision tracking
Official repo for "Cardiverse: Harnessing LLMs for Novel Card Game Prototyping" at EMNLP 2025
a list of disposable email domains
🪞 Make your agents recursively self-improve
Autonomous experiment loop extension for pi
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for p...
Sub2API 一站式开源中转服务,让 Claude、Openai 、Gemini、Grok订阅统一接入,支持拼车共享,更高效分摊成本,原生工具无缝使用。
Your personal intelligence agent. Watches the world from multiple data sources and pings you when something changes.
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr...
AI agents running research on single-GPU nanochat training automatically
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Open-source implementation of AlphaEvolve
首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows.
A claude code skill to delegate prompts to codex