Lists (2)
Stars
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
DeepSeek Harness finance plugin: direct market HTTP APIs, portfolio settings, model tools
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
Task-oriented AI Agent productivity platform
Browser automation CLI for AI agents
[ACL 2026 Main, SAC Highlight] FinSight: Towards Real-World Financial Deep Research. 🎯One ticker, one click, one publication-ready report.
A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows
slime is an LLM training framework for RL Scaling.
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
List of papers on hallucination detection in LLMs.
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
[ACL 2026 KnowFM] Awesome Agentic Deep Research Resources
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics rec…
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
Recipes to train reward model for RLHF.
HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
My learning notes for ML SYS.
FinRL®: Financial Reinforcement Learning. 🔥
SGLang is a high-performance serving framework for large language models and multimodal models.
A collection of prompts, system prompts and LLM instructions
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models