#3333rd of 33 in Agent frameworks and SDKs
rasa
Python framework for building contextual text and voice assistants
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 21.3k
- License
- Apache-2.0
- Last commit
- Dec 2025
- Last release
- Jan 2025
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Rasa Open Source is a Python framework for building contextual text and voice assistants, with connectors for Slack, Telegram, Twilio, Facebook Messenger, Microsoft Bot Framework and others. The repository is in maintenance mode. The README points new work to Hello Rasa, a browser playground built on the CALM engine, where an LLM handles dialogue understanding and flows enforce business logic.
Who it is for: Teams maintaining Rasa chatbots or building channel-based assistants in Python
Strengths
- Built-in connectors for Slack, Telegram, Twilio, Mattermost, Rocket.Chat, Webex and custom channels
- Apache-2.0 license, installable from PyPI, buildable from source with Poetry
- Handles layered multi-turn conversations with business logic kept in code
- Semantic Versioning with a published release and maintenance policy
Weaknesses
- Maintenance mode; README directs new development to Hello Rasa and CALM
- Last release is 2025-01-14, so releases have slowed
- Hello Rasa is a hosted playground; scaling path leads to the Rasa Platform
- README gives no hardware requirements, ports or supported model list
What it needs
- Docker + Compose
- Needs Python, Poetry (for development)
Also in Agent frameworks and SDKs
See all 33| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 92 out of 100 |
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 87 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 84 out of 100 |