8000 liziniu (Ziniu Li) / Starred · GitHub
[go: up one dir, main page]

Skip to content
View liziniu's full-sized avatar

Block or report liziniu

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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

DeepInfer: High-performance, large-scale inference framework for DeepSeek models

Python 26,147 3,222 Updated Nov 3, 2026

A Long-Horizon Benchmark for Self-Improving Inference Systems

Python 167 10 Updated Oct 26, 2026

FrontierSmith, a new system that uses AI to synthesize open-ended coding problems at scale

Python 84 6 Updated Oct 17, 2026

A benchmark for evaluating AI agents on frontier ultra long-horizon auto research tasks.

Python 172 18 Updated Aug 30, 2026

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

Python 140 11 Updated Nov 15, 2026

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fre…

Python 1,874 196 Updated Nov 11, 2026

Open-source implementation of AI-powered academic writing workspace inspired by OpenAI Prism, featuring LaTeX editing, PDF preview, and intelligent AI assistance

TypeScript 405 44 Updated May 12, 2026

Model Context Protocol (MCP) server that lets AI assistants read Overleaf projects, parse LaTeX document structure, and push section-level edits back via Git. Compatible with Claude Desktop, Cursor…

JavaScript 362 47 Updated May 3, 2026

The control plane for 24/7 always-on agents. Turn long-horizon goals into verifiable results across Codex, Claude Code, and custom runtimes—from local SQLite to team scale.

Python 6,708 636 Updated Nov 17, 2026

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Elixir 28,069 2,895 Updated Sep 15, 2026

A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

Python 1,359 150 Updated Nov 17, 2026

Draw and edit draw.io diagrams by chatting with an AI. Web app, desktop app, and an MCP server for Claude Code, Cursor, Codex and VS Code.

TypeScript 37,009 3,838 Updated Nov 17, 2026

The math library of Lean 4

Lean 4,490 1,867 Updated Nov 17, 2026

Get the main content of any page as Markdown.

TypeScript 10,070 477 Updated Oct 25, 2026

Uni-Agent is a framework for training long-horizon agents.

Python 732 158 Updated Nov 17, 2026

Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

Python 31,277 3,353 Updated Nov 16, 2026

code for "Tying the Loop - Tied Expert Layers in Mixture-of-Experts Language Models"

Python 15 2 Updated Jun 16, 2026

Code and Data for paper "GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?"

Shell 218 14 Updated Oct 22, 2026

Lightweight coding agent that runs in your terminal

Rust 135,603 21,500 Updated Nov 17, 2026

Skill to give Claude Code (and any coding agent) the ability to generate beautiful and practical Excalidraw diagrams.

Python 5,277 600 Updated Mar 1, 2026

DeepGEMM: clean and efficient BLAS kernel library on GPU

Cuda 9,201 1,533 Updated Oct 20, 2026

verl Zero-Mismatch Dense/MoE HuggingFace Rollout

Python 77 9 Updated Nov 9, 2026
Python 122 11 Updated May 11, 2026

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

Python 5,614 813 Updated Nov 17, 2026

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

Python 1,707 203 Updated Nov 17, 2026

An asynchronous streaming data management module for efficient post-training.

Python 175 58 Updated Nov 13, 2026

Experimenting Heuristic Learning with ImageNet

Python 70 6 Updated May 25, 2026

MyPhoneBench: Do Phone-Use Agents Respect Your Privacy?

Python 26 Updated Apr 3, 2026

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

Python 1,117 74 Updated May 12, 2026

[ICLR'26] Stronger-MAS: A RL Framework for multi LLM agent system; [arxiv] MetaAgent-X: End-to-End Reinforcement Learning Automatic Multi-Agent Systems

Python 229 28 Updated May 15, 2026
Next
0