Strands Agents 1.24.0 released
A feature release adding decision model routing, explicit cache points for GPT models, and improved error handling across multiple platforms.
What changed in 1.24.0
- ClassifierStrategy can now route with any DecisionModel, and DecisionModel can be used as a HumanInTheLoop classifier.
- OpenAI GPT-5.6+ models get explicit cache points placed by default.
- Fixed error detection for Nova and OpenAI-style Bedrock context overflow, and improved throttling classification for Gemini.
- Tool results now correctly report maxTokens when cut off, and transient request failures in VercelModel and GoogleModel are retried.
- Amazon Nova models now receive toolResult status, and summarizer fallback truncates largest text blocks first.
Summarised by AgentGid from AWS's official release notes on GitHub, as reported there; read the original before relying on it. Price, status and release dates come from our daily data.
Strands Agents at a glance
| What it is | AWS's open-source SDK for building and running AI agents in Python and TypeScript: a model-driven agent loop that runs in your own process with no hosted control plane; the same repository holds a harness, a CLI, MCP su… |
|---|---|
| Latest version | 1.65.0, Nov 13, 2026. This page is about an earlier release. |
| Release pace | 22 stable releases in the last 30 days; 1.24.0 came the same day as the previous one |
| Price | Free (OSS). Strands Agents is open source and free to use; you pay only for the models and infrastructure it runs on. (checked Nov 4, 2026) |
| Downloads, last 7 days | 8.9M up 0.8% |
| Gid Score | 55 #10 in Agent frameworks and SDKs |