Skip to content
View mmjzmy's full-sized avatar

Highlights

  • Pro

Block or report mmjzmy

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

Agentic Harness Engineering Beta: Requirement-Centered Evolution of Agent Harnesses. On held-out tasks pass@1 rises from 21.9% to 33.3% with 40.8% fewer tokens. A user simulator raises requirements…

Python 5 1 Updated Nov 20, 2026

Sage S2.1 Flash — A scientific multimodal model. Explore through reasoning. Verify through action.

36 Updated Nov 17, 2026

Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Be…

Python 982 107 Updated Oct 30, 2026

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

Python 3,386 640 Updated Nov 21, 2026
Python 12 Updated Oct 19, 2026

LightningRL: Breaking the Accuracy–Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning

Python 33 Updated Apr 25, 2026

Ultra-light Harness scaffolding for AI agents, a mini version of claude code

Python 977 353 Updated Jun 10, 2026

Reverse-engineering Claude Code's 512K LOC TypeScript source: agent loop, tool system, permission model, Grove training pipeline, anti-distillation defense

Python 111 18 Updated May 1, 2026

Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai

Python 30,284 3,747 Updated Nov 22, 2026

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

JavaScript 308,386 45,386 Updated Nov 20, 2026

🙌 OpenHands: AI-Driven Development

TypeScript 93,972 12,577 Updated Nov 22, 2026

We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that Sora-2 surpasses GPT5 by 10% on eyeballing puzzles and reache…

Python 319 6 Updated Aug 23, 2026

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Python 80,705 12,877 Updated Nov 15, 2026

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

Python 20,164 1,533 Updated Feb 27, 2026

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Python 169,312 35,260 Updated Nov 22, 2026

Python of formal math

Rust 696 11 Updated Nov 18, 2026

TexTeller can convert image to latex formulas (image2latex, latex OCR) with higher accuracy and exhibits superior generalization ability, enabling it to cover most usage scenarios.

Python 765 76 Updated Aug 22, 2025

🌟 Wiki of OI / ICPC for everyone. (某大型游戏线上攻略,内含炫酷算术魔法)

TypeScript 27,211 4,705 Updated Nov 21, 2026

Intro to Reinforcement Learning (强化学习纲要)

3,613 497 Updated Jul 25, 2020
Python 930 97 Updated Jul 6, 2023

Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB / Octave

Python 1,648 449 Updated Jan 11, 2023

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

MATLAB 18,559 1,734 Updated Nov 10, 2026

A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.

29,528 3,237 Updated Sep 30, 2025