Autocomp: AI Code Optimizer for Tensor Accelerators

A time traveling resource monitor for modern Linux systems

Perplexity open source garden for inference technology

Public repository for Skills

RAM is all you need

Accelerate inference without tears

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

A lightweight, powerful framework for multi-agent workflows

AgentScope: Agent-Oriented Programming for Building LLM Applications

MiroThinker is a series of open-source agentic models trained for deep research and complex tool use scenarios.

A PyTorch Library for Multi-Task Learning

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors

NSFOCUS API_Sword：A Burp Suite extension, Automatically recursively collect API endpoints from any response

AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

Invoicing, Time tracking, File reconciliation, Storage, Financial Overview & your own Assistant made for Freelancers

RL with Experience Replay

Automatic solver for plane geometry problems.

Linux namespaces and seccomp-bpf sandbox

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

[Preprint] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.

Open-source implementation of AlphaEvolve

rl from zero pretrain, can it be done? yes.