Agents Sdk Python Packages

google-adk

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

agentops

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

calfkit

🐮 Build decentralized multi-agent systems with dynamic agent-to-agent discovery and collaboration

memmachine-client

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

lauren-ai

First-party AI/LLM companion to the lauren web framework. Brings large language model agents into the same decorator-first, DI-driven, module-scoped programming model the rest of Lauren uses.

memmachine-common

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

softwareai

SoftwareAI is a framework with the aim of creating a software/application development company/organization governed by AI, its objective is not just to create the software with updates, documentation, schedules and spreadsheets, SoftwareAI is capable of running a software company completely with all the teams that make up a software company

memmachine-server

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

gigachain-text-splitters

⚡ Набор решений для разработки LLM-приложений на русском языке с поддержкой GigaChat ⚡

runtimeuse-client

Client library for AI agent runtime communication over WebSocket

calfkit-mesh

Deploy event-driven, distributed AI agents with Calfkit broker

rowboat

Open-source AI coworker, with memory

gigachain-experimental

Building applications with LLMs through composability

gigachain-cli

CLI for interacting with LangChain

gigachain-openai

An integration package connecting OpenAI and LangChain

rag-agent-eval-ci

CI evaluation framework for RAG and AI agents: groundedness, retrieval quality, hallucination, citations, latency, cost, and regression gating before production.

pi-ai-py

Python port of @mariozechner/pi-ai — unified LLM streaming API with OAuth authentication

pegasus-ai

A lightweight terminal agent framework for long-running modular agents

artemis-agents

A production-ready framework for structured multi-agent debates with adaptive evaluation, causal reasoning, and built-in safety monitoring.

softwareai-engine-library

O motor da biblioteca é liberado através do pip para a sincronia do motor em múltiplos agentes

modal-agents-sdk

This package wraps the Claude Agent SDK to execute AI agents in secure, scalable Modal containers. It provides progressive complexity—simple usage mirrors the original Agent SDK, while advanced features expose Modal's full capabilities (GPU, volumes, image customization, etc.).

runcycles-openai-agents

Runtime budget, action, and audit authority for the OpenAI Agents SDK — enforce LLM cost limits, tool call caps, and audit trails before execution.

gigachain-huggingface

An integration package connecting Hugging Face and GigaChain

open-responses

Self-hosted alternative to OpenAI's Responses API compatible with Agents SDK and works with all model providers (Claude/R1/Qwen/Ollama etc)