In Context Learning Python Packages

synthefy-nori

Open-source tabular foundation model for fast, training-free regression with predictive distributions.

synalinks

Keras based framework for neuro-symbolic LM systems

smashed

SMASHED is a toolkit designed to apply transformations to samples in datasets, such as fields extraction, tokenization, prompting, batching, and more. Supports datasets from Huggingface, torchdata iterables, or simple lists of dictionaries.

fintfm

A tabular foundation model for corporate credit risk, pretrained only on synthetic data and measured in public, including where it loses.

lightpfn

LightPFN: a 4.6M-parameter tabular foundation classifier trained only on synthetic data, Apache 2.0, CPU/CUDA/ROCm/Vulkan.

xenoverse

Benchmarking general decision-making with open & random worlds

ace-playbook

ACE — Agentic Context Engineering: evolving, self-improving context playbooks for LLM agents. Faithful ICLR 2026 implementation with OpenAI Agents SDK support.

routefm-router

Official implementation of “Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing” (arXiv:2609.37362).

fasticrl

In-Context Reinforcement Learning for LLMs — no fine-tuning, no gradient updates.

openicl

OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.

tabctx

Multi-tenant context caching and serving for tabular in-context-learning foundation models (TabICL, TabPFN, and similar)

easyinstruct

[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.

thinkretrieve

[EMNLP 2026 Findings] Retrieval-augmented test-time scaling: inject retrieved worked examples into a reasoning model's thinking trace, mid-thought.

daml-rag-framework

🧠 DAML-RAG: Domain-Adaptive Multi-source Learning RAG Framework | GraphRAG混合检索 + 推理时学习 + 教师-学生双模型协作 | Production-ready vertical domain AI solution

fasticle

ICLE is a multi-agent AI framework that dynamically trains and orchestrates specialized Expert Agents to solve complex, multi-step tasks.

synthefy-tabular

Open-source tabular foundation model for fast, training-free regression with predictive distributions.

openicl-nolabel

OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.

mseep-synalinks

Keras based framework for neuro-symbolic LM systems

staicc

A standardized toolkit for classification task on In-context Learning. Official code implementation of paper: "StaICC: Standardized Evaluation for Classification Task in In-context Learning"