Conversational Ai Python Packages

elevenlabs

The official Python SDK for the ElevenLabs API.

rasa

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

assistant-stream

Typescript/React Library for AI Chat 💬🚀

pipecat-ai-flows

Open source conversation framework for structured Pipecat dialogues

rasa-pro

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

simpletransformers

Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

typecast-python

The official SDK for the Typecast API. (Python, JS/TS, C/C++, C#, Java, Kotlin, Go, Rust, Swift, Zig, PHP, Dart/Flutter, Ruby)

lumen

Illuminate your data. Agent framework turning natural language into SQL, charts, dashboards and reports.

dv-pipecat-flows

Open source conversation framework for structured Pipecat dialogues

massgen

🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai

convokit

ConvoKit is a toolkit for extracting conversational features and analyzing social phenomena in conversations. It includes several large conversational datasets along with scripts exemplifying the use of the toolkit on these datasets.

rasa-core

Rasa Core is now part of the Rasa repo: An open source machine learning framework to automate text-and voice-based conversations

rasa-nlu

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

chatflow-agent

Lightweight, async multi-agent framework with native SQLite persistence and handoffs for WhatsApp, Telegram, Webhooks, and CLI. Production-hardened with HMAC webhook security, automatic retries, and turn rollback. Supports OpenAI, Claude, Gemini, and local LLMs.

premove-itn

Premove ITN: context-aware inverse text normalization for English voice-agent transcripts.

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.

tring

Open-source voice agent stack: one agent contract, any runtime (cascade / speech-to-speech / hybrid), local-first, cost-transparent.

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.

superdialog

Low latency framework for realtime conversations.

standin-sdk

StandIn: put your AI agent into Microsoft Teams calls as a real participant, in your own tenant. agent backends (OpenClaw, Hermes Agent, LiveKit, ElevenLabs, OpenAI Realtime, Deepgram, Cartesia)

impressmem

给 AI Agent 的印象式记忆系统 — 零向量数据库，单依赖 Redis，不调用 LLMImpression-style memory for AI Agents — zero vector DB, single dep (Redis), no LLM calls

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.

attenlabs-saa

Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and the agent's own TTS echo never trigger it. No wake word, model-agnostic, drop-in for LiveKit, Pipecat, ElevenLabs, Twilio, and OpenAI. The layer your VAD and turn detection are missing.

arksim

Find your agents errors be fore your real users do