In Context Learning Python Packages

synalinks

From idea to production in just few lines: Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices

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.

ace-playbook

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

openicl

An open source framework for in-context learning.

fasticrl

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

xenoverse

Benchmarking general decision-making with open & random worlds

easyinstruct

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

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

staicc

A standardized toolkit for classification task on In-context Learning.

mseep-synalinks

Graph-Based Programmable Neuro-Symbolic LM Framework

openicl-nolabel

This is a modified version based on the original openicl 0.1.8 for certain research usages.