# AWS and UC Berkeley release Infinity agent runtime

> **Key takeaway:** Infinity is an Apache 2.0 licensed runtime that allows LLM agents to be suspended and resumed like stackless coroutines to enable massive concurrency.

**Published:** 2026-10-23T16:58:32+00:00 
**Source:** AWS Open Source Blog 
**Category:** bigtech-foss 
**Canonical URL:** https://fosswire.org/news/aws-and-uc-berkeley-release-infinity-agent-runtime.html 

## Summary
AWS and UC Berkeley have introduced Infinity, a research project under the Hydro initiative designed to handle extreme concurrency in AI agents. By treating agents like stackless coroutines, the runtime saves conversation history to a store and suspends the process during tool calls or wait periods. This approach allows for running up to 75,000 agents on a Raspberry Pi 5 and enables efficient deployment on serverless platforms.

## How Infinity manages agent concurrency
- Uses a **stackless coroutine** model where agents are executed in bounded **slices**.
- Instead of holding memory during tool calls, the runtime persists the conversation history to a **pluggable store** and discards in-memory state.
- Tool results and user inputs arrive via a **shared input queue**, triggering a new execution slice.
- Designed to be extremely lightweight; can fit **75,000 concurrent agents** in 8 GB of RAM on a Raspberry Pi 5.
- Enables **serverless deployment** because the function can terminate while the agent is suspended waiting for a tool.

## Why it matters
Infinity provides a way to scale AI agentic workflows without the massive memory overhead typically required by blocking processes, making complex agent systems viable on edge hardware and serverless infrastructure.