frameworks & SDKs: 109 curated resources
frameworks & SDKs
109 resources · page 4 of 4
Kimi K2: Open Agentic Intelligence
arXiv paper (2025) Kimi K2 technical report: MuonClip optimizer and agentic post-training.
Long Horizon Document Agents (LlamaIndex)
by LlamaIndex
LlamaIndex post on designing long-horizon agents that process and act on documents.
MAPIE
by MAPIE project (Capgemini Invent and Quantmetry)
MAPIE documentation: Python library for conformal prediction intervals and sets for any model.
Metaflow documentation
by Metaflow project (Outerbounds)
Metaflow documentation: open-source framework from Netflix for building and running data science and ML workflows.
Nanbeige 4.2-3B official model card
Hugging Face model card for Nanbeige4.2-3B with architecture, usage and evaluation details.
PennyLane documentation
PennyLane documentation: Python library for differentiable quantum computing and hybrid quantum-classical ML.
PyGOD
by PyGOD team
PyGOD documentation: Python library for outlier and anomaly detection on graphs.
ReAct
by Shunyu Yao et al. (Princeton University and Google Research)
arXiv paper (2022) "ReAct: Synergizing Reasoning and Acting in Language Models", introducing ReAct, interleaving reasoning traces and tool actions in language models.
Scaling Managed Agents: decoupling brain from hands
by Anthropic
Anthropic engineering post on the architecture of its hosted Managed Agents harness, separating model reasoning from execution.
SHAP documentation
SHAP documentation: game-theoretic method and library for explaining ML model predictions.
AI SDK docs: Loop control
by Vercel
Vercel AI SDK documentation on loop control: stop conditions and step control for agent loops.
Berkeley Advanced LLM Agents (SP25)
Berkeley CS294/194-280 Advanced Large Language Model Agents (Spring 2025): lectures on reasoning, coding agents and agent safety.
SpikingJelly
by SpikingJelly team (Peking University)
SpikingJelly documentation (in Chinese): PyTorch framework for deep learning with spiking neural networks.