#3636th of 70 in Agent frameworks and SDKs
praisonai
Python SDK and CLI for building multi-agent workflows with tools and MCP
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 9.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
6,097 on 1 Apr 20269,283 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
PraisonAI is a Python framework (praisonaiagents SDK plus praisonai CLI) for defining agents with instructions, tools, memory, knowledge and guardrails, and chaining them in AgentFlow graphs with routing, parallel steps and loops. Tools can run in remote sandboxes such as Docker, E2B, Modal, Daytona and Fly.io. Optional extras add a Telegram/Slack/Discord dashboard, a visual flow builder and a chat UI.
Who it is for: Python developers building multi-agent workflows with optional remote sandboxes
Strengths
- Workflows can be written in Python or in YAML with no code
- Tools can run in Docker, E2B, Modal, Daytona, Fly.io, SSH or subprocess
- Explicit loop controls: iteration cap, budget ceiling, doom-loop detection on by default
- Lists 24 providers including Ollama and vLLM; MCP supported
Weaknesses
- Large surface (SDK, CLI, Claw, Flow, UI) split across several pip extras
- Quick start assumes an OpenAI API key; local model setup is left to provider examples
- README is marketing-heavy; production deployment and scaling details are unknown
- No Dockerfile or compose file detected in the repository
What it needs
- no GPU
- Docker + Compose
- Needs LLM provider API key (e.g. OpenAI) or local Ollama/vLLM, Optional sandbox backends: Docker, E2B, Modal, Daytona, Fly.io
- Models: OpenAI, Anthropic, Google Gemini, Ollama, vLLM
Also in Agent frameworks and SDKs
See all 70| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 94 out of 100 |
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 89 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| #4 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 89 out of 100 |
| #5 | mastraTypeScript framework for building AI agents and workflows | 89 out of 100 |