Skip to content
View ijingo's full-sized avatar
🐽
🐽

Organizations

@4paradigm

Block or report ijingo

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
Showing results

A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training

Python 850 58 Updated Jun 15, 2026

High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and SGLang.

Rust 142 20 Updated Jun 15, 2026

Nano vLLM

Python 14,041 2,219 Updated Apr 26, 2026

FlashInfer: Kernel Library for LLM Serving

Python 5,797 1,050 Updated Jun 15, 2026
Python 1,292 134 Updated May 20, 2026

PersonaPlex code.

Python 10,018 1,397 Updated Mar 2, 2026

🧠「大模型」2小时完全从0训练64M的小参数LLM!Train a 64M-parameter LLM from scratch in just 2h!

Python 51,778 6,652 Updated Jun 1, 2026

[ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

Python 276 13 Updated Apr 18, 2026

A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.

90,446 10,742 Updated Jun 15, 2026

A ~9M parameter LLM that talks like a small fish.

Python 3,244 285 Updated Apr 15, 2026

Development repository for the Triton language and compiler

MLIR 19,447 2,939 Updated Jun 15, 2026

Self-evolving memory across Agent and platform. The one portable memory layer for every agent they use - Claude Code, Codex, OpenClaw, Hermes, and more

Python 7,485 734 Updated Jun 15, 2026

The paper list of "Memory in the Age of AI Agents: A Survey"

2,139 103 Updated Mar 4, 2026

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

Python 71,237 9,656 Updated Jun 15, 2026

A terminal workspace with batteries included

Rust 33,642 1,260 Updated Jun 15, 2026

Experimental self-improving multi-agent coding system: a root agent recursively decomposes goals and delegates to specialist subagents, learning from failures by mutating a git-backed agent genome.…

TypeScript 57 7 Updated Jun 8, 2026

An agentic skills framework & software development methodology that works.

Shell 228,740 20,347 Updated Jun 15, 2026

Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context

Rust 284 37 Updated May 27, 2026

Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

TypeScript 27,061 2,353 Updated Jun 15, 2026

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

Python 472 51 Updated Jun 15, 2026

The Generative UI framework

TypeScript 15,193 820 Updated Jun 15, 2026

Claude Code excalidraw skill

70 6 Updated Jan 8, 2026

Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.

Rust 80 4 Updated Apr 6, 2026

SGLang is a high-performance serving framework for large language models and multimodal models.

Python 29,049 6,543 Updated Jun 15, 2026
Python 22,763 2,231 Updated Jun 11, 2026

HY-Motion model for 3D human motion or 3D character animation generation.

Python 2,395 197 Updated May 25, 2026

Wan: Open and Advanced Large-Scale Video Generative Models

Python 16,232 2,013 Updated Mar 17, 2026

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Python 117,116 13,696 Updated Jun 15, 2026

Wan: Open and Advanced Large-Scale Video Generative Models

Python 16,260 2,863 Updated Mar 5, 2026
Next