AI Agents
ten-framework
Open-source framework for conversational voice AI agents
★ 11.1k starsUnknown
View guide →// agents · RasaHQ/rasa
rasa
rasa is an open-source ai agents project by RasaHQ (RasaHQ/rasa on GitHub). It has 21,343 GitHub stars and 4,918 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 24 July 2026.
The veteran open-source framework for conversational AI that you host.
★ 21.3k stars⑂ 4.9k forksApache-2.0updated 2026-07
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- RasaHQ/rasa
- GitHub stars
- 21,343
- Forks
- 4,918
- License
- Apache-2.0
- Last updated on GitHub
- 24 July 2026
- Category
- AI Agents
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Define the job
Know what you want the agent to accomplish before touching any code.
- Get the code
Clone the repo and read the README's requirements section.
- Wire up dependencies
Install what's needed and add API keys or configuration.
- Take it for a spin
Run the quickstart example, then iterate from there.
// features
Why people love it
NLU + dialogue management
Understand intents and manage conversations.
Channel connectors
Slack, Facebook, voice, and more.
On-premise deployment
Your data never has to leave.
Voice support
Beyond text: voice assistants too.
Conversation-driven development
Improve from real transcripts.
Production track record
Years of enterprise deployments.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/RasaHQ/rasa.git cd rasa - Step 2 — Create a venv and install
Isolate dependencies, then install requirements.
python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt - Step 3 — Run it
Launch using the entry point shown in the README.
python -m rasa # check README for the exact command
// use cases
What you can build
- Build a self-hosted support chatbot.
- Add voice assistants to products.
- Keep conversation data on-premise.
- Iterate bots from real transcripts.
Advertisement
// faq
Questions, answered
Who maintains rasa?
It is an open-source project at RasaHQ/rasa with 4918 forks. Check the contributors tab and recent commits to judge how active maintenance is.
Is rasa free to use?
Yes — Apache 2.0 allows commercial use and modification. Keep the license and notice files, and note it includes a patent grant.
Is Rasa still maintained?
The last push was July 2026 — check recent commits and issues on GitHub to judge current activity before adopting.
Rasa vs LLM chatbots?
Rasa is deterministic and self-hosted: NLU plus dialogue policies you control, versus a black-box LLM API.
How do I get started?
Clone the repo and follow the README quickstart — the docs at https://rasa.com/docs/rasa/ walk through setup.
// keep exploring
Similar tools
AI Agents
QwenPaw
Your personal AI assistant — self-host it, chat anywhere, extend everything.
★ 35.5k starsApache-2.0
View guide →AI Agents
mlx
Apple's array framework for running ML efficiently on Apple silicon.
★ 28.7k starsMIT
View guide →AI Agents
RAG-Anything
One RAG framework for everything — including multimodal documents.
★ 23.5k starsMIT
View guide →AI Agents
IsaacLab
Isaac Lab — NVIDIA's unified framework for robot learning, with 30+ environments and multi-physics simulation.
★ 8.3k starsBSD-3-Clause
View guide →AI Agents
eve
Vercel's open framework for building agents that run anywhere.
★ 5.5k starsApache-2.0
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if rasa is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to rasa — keep exploring the shelf either side of it.
- prime-agent★ 21.6k
A self-improving agent for coding workflows and long-running autonomous tasks
- SWE-agent★ 20.5k
Give it a GitHub issue and it tries to fix the code for you - the original SWE-bench agent
- coze-studio★ 21.7k
A visual all-in-one platform for building, debugging, and deploying AI agents.
- suna★ 20.3k
Kortix - the open-source AI operating system: agents, skills and memory as files in a repo
- adk-python★ 21.7k
Google's code-first toolkit for building real AI agents.
- Tongyi Deep Research★ 20.0k
Tongyi Deep Research - Alibaba's open-source deep research agent and 30B model
Get rasa
Free and open — grab the source, star the repo, and start creating.