Evaluate retrieval models on agentic benchmarks using Codex CLI as the agent harness

"QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks"

An active paper-reading skill that reconstructs author reasoning, explains methods mechanistically, stress-tests assumptions, and generates follow-up research ideas.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents

Evaluation harness for Apodex-1.0 on public deep-research benchmarks.

A Skill Library for Automated Machine Learning

Native macOS semantic search over your local files - text, images, audio, video in one vector space, on-device on Apple silicon.

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

A Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Self-Evolving Agents.

An extensive and commented list of resources on Late-Interaction Multivector Retrieval.

Production-grade engineering skills for AI coding agents.

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Me…

Elevate your AI research writing, no more tedious polishing ✨

The official repository of "A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications".

The official GitHub page for the paper "Agent Systems with Harness Engineering"

An agentic skills framework & software development methodology that works.

Codes and data for paper: GrepSeek: Training Search Agents for Direct Corpus Interaction

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Qwen3-8B trained with pure RL, reaching 36+ BrowseComp Plus token-F1 in 250 steps.

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

🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.

A collection of Awesome Finance Agent Skills for free and easy to start | 一系列开源免费的金融分析Agent Skills

Lightweight and Scalable Post-training: The Ray-Free, Debug-Friendly Alignment Stack with Megatron-native simplicity.

No fortress, purely open ground. OpenManus is Coming.

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.