PHA dev just open-sourced the fastest production-ready multi-agent framework on GitHub, and it benchmarks 1,209x faster than LangGraph in agent startup speed.
If you're building AI bots, automations, or multi-agent systems, this is worth your attention.
If you're building AI bots, automations, or multi-agent systems, this is worth your attention.
Here's what's inside:
3.77 microseconds average agent startup time — faster than OpenAI Agents SDK, Agno, PydanticAI, and LangGraph. Benchmark-proven.
Single agent, multi-agent, parallel execution, routing, loops, and evaluator-optimizer patterns — all built in, zero extra setup.
Persistent memory out of the box — short-term, long-term, entity, and episodic memory with a single parameter. No extra dependencies.
100+ AI models supported — OpenAI, Claude, Gemini, Groq, DeepSeek, Mistral, Ollama, and 90 more. Switch models by changing one line of code.
Full MCP Protocol support — connect to any external tool or expose your agent as an MCP server for Claude, Cursor, or any other client.
Built-in 24/7 scheduler — your agents run on their own without you manually triggering anything.
Don't want to write code at all?
The CLI handles everything — deep research, memory management, workflow execution, session handling, all from your terminal.
pip install praisonaiagents
One install. That's it.
You do not have permission to view the full content of this post. Log in or register now.GitHub stars. Open source. Completely free.
If you're building anything with AI agents — this is the framework to watch.