CheetahClaws (Nano Claude Code): A Fast, Easy-to-Use, Python-Native Personal AI Assistant for Any Model, Inspired by OpenClaw and Claude Code, Built to Work for You Autonomously 24/7.

Scalable data pre processing and curation toolkit for LLMs

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

Use Codex from Claude Code to review code or delegate tasks.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

Official repository of OpenEarth-Agent

A massively multilingual modern encoder language model

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Spherical Merge Pytorch/HF format Language Models with minimal feature loss.

Tools for merging pretrained large language models.

[COLM 25] Phased Training for LLM-powered Text Retrieval Models Beyond Data Scaling

Claude Code skill that translates entire books (PDF/DOCX/EPUB) into any language using parallel subagents

The repo of KINA (Knowledge Index of Noah's Ark) benchmark.

用Claude Code skills打造我的论文流水线

Post-training with Tinker

📚 Claude Code plugin that automates research papers study with automatic material generation, code demonstrations, and interactive web viewer.

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

The open agent skills tool - npx skills

Give your agents the power of the Hugging Face ecosystem

Get 10X more out of Claude Code, Codex or any coding agent

Code Editor for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine

[CVPR 2026] Direction-aware 3D Large Multimodal Models

[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

PyTorch building blocks for the OLMo ecosystem

🤗 smolagents: a barebones library for agents that think in code.

User friendly and accurate binder design pipeline

Paper: “MEMRL: SELF-EVOLVING AGENTS VIA RUNTIME REINFORCEMENT LEARNING ON EPISODIC MEMORY” Open-Source Code

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.