Skip to content
View zxyscz's full-sized avatar

Block or report zxyscz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Starred repositories

Showing results
Python 84 7 Updated Mar 11, 2025

Democratizing Reinforcement Learning for LLMs

Python 5,639 576 Updated Jun 22, 2026
Python 151 33 Updated May 13, 2026

τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Python 1,404 360 Updated Jun 11, 2026

A high-throughput and memory-efficient inference and serving engine for LLMs

Python 83,553 18,319 Updated Jun 22, 2026

Get JSON values quickly - JSON parser for Go

Go 15,525 901 Updated May 14, 2026

OpenClaw-RL: Train any agent simply by talking

Python 5,516 597 Updated May 23, 2026

A browser-based desktop where AI Agent operates every app through natural language.

TypeScript 1,213 157 Updated Jun 3, 2026
Python 89 8 Updated Dec 23, 2025

RL research on Android devices.

Python 1,225 111 Updated Jun 22, 2026

dLLM: Simple Diffusion Language Modeling

Python 2,589 271 Updated Jun 12, 2026

SkillsBench evaluates how well skills work and how effective agents are at using them.

PDDL 1,377 319 Updated Jun 21, 2026

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

Python 5,321 524 Updated Jun 22, 2026

Agent Skills to help developers using AI agents with Supabase

TypeScript 2,269 161 Updated Jun 9, 2026

A LLM-based Agent that predict its tasks proactively.

Python 614 62 Updated May 12, 2026

The agent-native LLM router for OpenClaw. 41+ models, <1ms routing, USDC payments on Base & Solana via x402.

TypeScript 6,585 608 Updated Jun 18, 2026

Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.

Python 256 20 Updated May 21, 2026

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…

JavaScript 83,714 7,233 Updated Jun 21, 2026
Python 13 Updated Apr 20, 2026
Python 291 23 Updated May 16, 2026

Moonshot's most powerful model

2,061 258 Updated Jan 31, 2026

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

TypeScript 379,944 79,543 Updated Jun 22, 2026

Kimi K2 is the large language model series developed by Moonshot AI team

10,867 857 Updated Jan 21, 2026

Dr. Zero Self-Evolving Search Agents without Training Data

Python 523 66 Updated Mar 23, 2026

SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

Python 3,529 364 Updated May 21, 2026

PhD Thesis work -- computational model of learning and memory in decision making in reinforcement learning tasks

Jupyter Notebook 13 6 Updated Oct 15, 2021

The code for NeurIPS 2025 paper "A-Mem: Agentic Memory for LLM Agents"

Python 906 93 Updated Mar 5, 2026

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Python 4,462 341 Updated Jan 14, 2026

slime is an LLM post-training framework for RL Scaling.

Python 6,664 962 Updated Jun 22, 2026

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

Python 940 88 Updated Jun 18, 2026
Next