Builds production multi-agent systems with a Python framework and low-code layer — self-reflection, tool use, and 100+ LLM support. Also runs as a CLI. Open source.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Multi-Agent Systems
Use PraisonAI to build collaborating multi-agent systems: ‹what you need›
- Self-Reflection
Use PraisonAI to add a self-reflection loop: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: github.com/MervinPraison/PraisonAI
Call the API
Auth An API key from PraisonAI
Its page: github.com/MervinPraison/PraisonAI
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- CLIAPI
- Auth
- API Key
- Skills
- 3
Skills
Multi-Agent Systems
Builds collaborating multi-agent systems with roles, tasks, and tools in Python or via low-code YAML.
Self-Reflection
Adds a self-reflection loop so agents critique and improve their own outputs before finishing.
Broad LLM Support
Runs agents against 100+ LLM providers with a consistent configuration across models.