Stars
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per re…
Agent skill that removes signs of AI-generated writing from text
DeepSeek Harness: Everything is a Plugin.
Lightweight coding agent that runs in your terminal
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
The agent that grows with you
qqhard / superpowers-ML
Forked from obra/superpowersAdaptation of Superpower in the ML field
TradingAgents: Multi-Agents LLM Financial Trading Framework
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Deep dive into Claude Code's source code— learn from the best agent implementation out there.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
End-to-end Generative Optimization for AI Agents
Professional financial data API for China A-shares, US & HK stocks. Python SDK with real-time quotes, K-line data & financial reports.
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"
[SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.
Official implementation of the paper "Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following"
The source code of our paper: 'DecIF: Improving Instruction-Following through Decomposition'
A simple plug-in framework that corrects bias and computes confidence intervals in reporting LLM-as-a-judge evaluation, and an adaptive algorithm that efficiently allocates calibration samples to r…
Free, open source crypto trading bot
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels