Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Strands Agents by AWS

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 support and evals.

Agent frameworks and SDKs Vendor agent SDKOpen source · Apache-2.0Free to start

Use it in: API / SDK Works with: MCP Local models Multi-agent

Price
Free (OSS)
free and open source
Popularity
#10 in Frameworks
Gid Score 56 / 100 · #10 of 50 ranked frameworks and SDKs
Trend
Steady
downloads up 3.8% over 30 days · up 1.3% last week
Development
Actively updated
latest 1.65.0, 7d ago
Community
9,252 GitHub stars
9M package downloads a week

Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number

What Strands Agents does

Strands Agents is a vendor agent SDK from AWS, first released in May 2025. You use it through a Python library and a TypeScript library. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from Amazon Bedrock, Anthropic, OpenAI and Google. It is used from Python and TypeScript. It is free and open source (Apache-2.0); you pay only for the models it calls.

Teams use it for: Workflow automation, Building apps, DevOps and CI, Testing, Incident response. See examples.

Key facts

MakerAWS
TypeVendor agent SDK
First releasedMay 2025
LicenseApache-2.0
InterfacesPython library, TypeScript library
Main languageTypeScript
Open issues and PRs1,284

Pricing

Strands Agents is open source and free to use; you pay only for the models and infrastructure it runs on.

Checked Nov 4, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (Apache-2.0)
  • Where you use itPython library, TypeScript library
  • Supports MCP?Yes
  • Model providersamazon, anthropic, openai, google, local
  • Subagents / multi-agent?Yes
  • Feature comparisonAll agents
  • Closest alternativeLangChain · all alternatives

What's new in Strands Agents: October 2026

Full monthly summary

October brought the general availability of bidirectional streaming for agents, along with expanded TypeScript support and new tools for agent composition. The month focused on making streaming interactions more powerful and standardizing agent capabilities across languages.

  • Bidirectional streaming API graduated to general availability with full console I/O support.
  • Token usage events now normalized across all agent types for consistent cost tracking.
  • New coding-agent skill added to expand what agents can accomplish out of the box.
  • Agent cancellation now works through the unified agent.cancel() method.

3 releases this month · summarised from the official release notes · all months

How teams use Strands Agents

All Strands Agents use cases · All use cases

Recipe

Stream low-latency agent speech with Kokoro TTS on Amazon SageMaker AI

An AWS blog post shows how to send each sentence from an AI voice agent to a hosted Kokoro-82M text-to-speech model as soon as it is generated. Audio playback can then begin befor…

As reported by AWS, sending only the first sentence cut mean time to first audio byte from 329.3 ms to 156.7 ms, a 52.4 percent relative improvement …

Strands AgentsAmazon SageMaker AIKokoro-82MWorkflow automation · Building apps
Case studyRescale

How Rescale built a test-failure triage agent with Strands Agents and AI-DLC

Rescale, a digital engineering platform company, built an agent that classifies and routes failures from its nightly end-to-end tests, using the AI-DLC methodology and the Strands…

As reported by AWS, classification agreement with human triage rose from 44% at initial deployment to 68% today.

Strands AgentsStrands Agents SDKClaude Opus 4.8 on Amazon BedrockTesting · Incident response
Recipe

Route agent requests between local SLMs and Amazon Bedrock with Strands Agents

An AWS blog walkthrough shows how to build an Adaptive Agentic Intelligence Framework with Strands Agents. A small local model handles routine requests, and complex analysis goes …

Routine requests such as device status checks and image analysis run locally with low latency and no cloud dependency. (as reported by AWS)

Strands AgentsOllamaAmazon BedrockWorkflow automation · DevOps and CI
Case studyCornerstone OnDemand

How Cornerstone OnDemand cut database diagnosis time with Strands Agents on Amazon Bedrock

Cornerstone OnDemand's three-person Enterprise DataOps team built Orion AI, a multi-agent system on Amazon Bedrock and Strands Agents, in six months. It speeds up database inciden…

As reported by AWS, database diagnosis time dropped from 45 minutes to 10 minutes, a 78% reduction.

Strands AgentsOrion AIAmazon BedrockIncident response · DevOps and CI

AgentGid articles about Strands Agents

All guides

Get started with Strands Agents

PyPIpip install strands-agents

These commands use the packages tracked on this page. The vendor may recommend a different installer.

What Strands Agents users report right now

All 1 reports, questions and fixes →

Fixed Users report that the Python SDK's agent trace span exported the full system prompt under a raw system_prompt attribute, outside the GenAI semantic conventions and the redaction setting meant to hide it. A merged pull request moved it to the standard attribute and routed it through redaction.

Reported on GitHub · 5 👍

The most discussed problems in its GitHub repository, checked Nov 12, 2026. Written by AgentGid in its own words; statuses and fix versions come from the project's own pages. Reports are users' accounts, not AgentGid tests.

Add-ons for Strands Agents: save tokens, add memory and tools

All agent tooling

Listed because each tool documents support for Strands Agents or for agent frameworks in general. Savings and results depend on your workload.

Compare Strands Agents with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
1
LangChainLangChain
79 41.1M up 5.7% down 2.7% 150K+76/day 1.5.22d ago Free (OSS)
2
LangGraphLangChain
75 20.1M up 5.5% up 29.2% 45.1K+48/day 1.2.23yesterday Free (OSS)
3
AI SDKVercel
68 47.2M up 3.9% up 38.4% 28.1K+30/day 7.0.1772d ago Free (OSS)
4 64 29.3M up 5.9% up 37.6% 8,588+9/day 0.2.185yesterday Free (OSS)
5
MastraMastra
63 3.7M up 14.9% up 49.9% 29.6K+23/day 1.84.02d ago Free (OSS)
6 62 7.2M up 4.8% up 38.9% 30.8K+21/day 0.25.02d ago Free (OSS)

Head to head: Strands Agents vs LangGraph · Strands Agents vs Claude Agent SDK · Strands Agents vs LangChain · Strands Agents vs OpenAI Agents SDK · Strands Agents vs AI SDK

Tools used with Strands Agents

All tools

What 127 public GitHub projects that depend on Strands Agents use with it, from their dependency files.

  1. Boto370.1%
  2. Strands Agents Tools66.9%
  3. python-dotenv47.2%
  4. Requests36.2%
  5. Model Context Protocol SDK (Python)33.9%
  6. AWS Bedrock AgentCore29.9%
  7. Pydantic28.3%
  8. Uvicorn26.0%
  9. FastAPI24.4%
  10. Streamlit23.6%

Used far more often here than in AI-built projects overall: what sets Strands Agents projects apart.

  1. opensearch-py11.8% · 246.2×
  2. retrying6.3% · 197.0×
  3. uv15.0% · 85.1×
  4. botocore20.5% · 67.4×
  5. Hypothesis4.7% · 59.1×
  6. Streamlit23.6% · 21.7×
  7. Tavily Python SDK5.5% · 21.5×
  8. Diagrams6.3% · 14.6×

Ratings from people who use Strands Agents

No ratings yet. Used Strands Agents? Rate it and say what it is good and bad at.

Strands Agents news

All AI agent news

  1. Agents in actionHot AWS Machine Learning Blog

    LoanPro's AI servicing assistant cuts account summaries from 3–5 minutes to under 15 seconds

    In an AWS blog post co-written with LoanPro, the lending platform describes a multi-agent assistant built with AllCloud. It runs on Amazon Bedrock AgentCore and the Strands Agents SDK and helps servicing agents get up to speed on a borrower's account during live calls.

  2. Release GitHub Releases

    Strands Agents 1.65.0 released

    feat(multiagent): async agent builders; report content-filtered and refused children as tool errors (3d741b47d); feat(site): add /frogs page (9b38e2e9c); feat(context)!: offload conditions decide granularity (typescript) (50a391e05) (+1 more release that day)

  3. Release GitHub Releases

    Strands Agents 0.4.0 released

    feat(site): add /frogs page (9b38e2e9c); feat(context)!: offload conditions decide granularity (typescript) (50a391e05); feat(mcp): add find_integrations tool backed by the catalog feed (085d4de61) (+2 more releases that day)

  4. Official AWS Machine Learning

    Build composable, interoperable multi-agent systems with A2A on AWS

    AWS demonstrates a multi-agent system using the Agent-to-Agent (A2A) protocol, with a LangChain orchestrator on ECS communicating with a Strands agent on Bedrock AgentCore via OAuth-authenticated calls.

What changed: recent Strands Agents releases

60 stable releases in the last 90 days · Monthly summary · Full changelog

1.65.0
  • feat(multiagent): async agent builders; report content-filtered and refused children as tool errors (3d741b47d)
  • feat(site): add /frogs page (9b38e2e9c)
  • feat(context)!: offload conditions decide granularity (typescript) (50a391e05)
  • feat(mcp): add find_integrations tool backed by the catalog feed (085d4de61)
  • feat(models): handle Bedrock InvokeModel in AnthropicModel (mid-stream errors, API version); add defaultEffort to the shared model info (py + ts) (860c07c26)
  • feat(injection)!: write injected text into history as an injected block (python) (228990b03)
1.25.0
  • feat(context)!: offload conditions decide granularity (typescript) (50a391e05)
  • feat(mcp): add find_integrations tool backed by the catalog feed (085d4de61)
  • feat(models): handle Bedrock InvokeModel in AnthropicModel (mid-stream errors, API version); add defaultEffort to the shared model info (py + ts) (860c07c26)
  • feat(injection)!: write injected text into history as an injected block (python) (228990b03)
  • feat(harness)!: drop todos from the default built-in plugins (23de8a852)
  • feat(site): add Decider product navigation (39de68ea7)
Earlier releases
0.4.0
  • feat(site): add /frogs page (9b38e2e9c)
  • feat(context)!: offload conditions decide granularity (typescript) (50a391e05)
  • feat(mcp): add find_integrations tool backed by the catalog feed (085d4de61)
  • feat(models): handle Bedrock InvokeModel in AnthropicModel (mid-stream errors, API version); add defaultEffort to the shared model info (py + ts) (860c07c26)
  • feat(injection)!: write injected text into history as an injected block (python) (228990b03)
  • feat(harness)!: drop todos from the default built-in plugins (23de8a852)
0.4.0
  • feat(site): add /frogs page (9b38e2e9c)
  • feat(context)!: offload conditions decide granularity (typescript) (50a391e05)
  • feat(mcp): add find_integrations tool backed by the catalog feed (085d4de61)
  • feat(models): handle Bedrock InvokeModel in AnthropicModel (mid-stream errors, API version); add defaultEffort to the shared model info (py + ts) (860c07c26)
  • feat(injection)!: write injected text into history as an injected block (python) (228990b03)
  • feat(harness)!: drop todos from the default built-in plugins (23de8a852)
0.4.0
  • feat(context)!: offload conditions decide granularity (typescript) (50a391e05)
  • feat(mcp): add find_integrations tool backed by the catalog feed (085d4de61)
  • feat(models): handle Bedrock InvokeModel in AnthropicModel (mid-stream errors, API version); add defaultEffort to the shared model info (py + ts) (860c07c26)
  • feat(injection)!: write injected text into history as an injected block (python) (228990b03)
  • feat(harness)!: drop todos from the default built-in plugins (23de8a852)
  • feat(site): add Decider product navigation (39de68ea7)
0.3.0
  • feat(cli): merge feature/cli-0.3.0 into main (b80085bcd)
  • feat(models): give Model.summarize() a client-side base implementation (75a0cdd99)
  • feat(vended-tools): make the shell tool's default timeout configurable (e0a6a229a)
  • feat(site): replace model provider logos with customer logos (75d49f89d)
  • feat(mcp): accept alternate phrasings in search_docs and fuse the rankings (21853498e)
  • feat(site): publish the integrations catalog as a versioned JSON feed (fb0f55edf)

Strands Agents popularity and usage data

Strands Agents was downloaded 9M times from PyPI in the week ending Nov 17, 2026, up 1.3% on the week before and up 3.8% over the last 30 days compared with the 30 before. The GitHub repository has 9,252 stars, 405 of them added in the last 30 days. The latest stable release is 1.65.0, published Nov 13, 2026; there were 22 stable releases in the past 30 days. It was mentioned in 5 Hacker News posts and comments over the last 30 days.

Downloads per dayPyPI, 7-day average 1.3M/day
GitHub starsrunning total 9,252
Hacker News mentionsposts and comments, rolling 7-day total 1 this week

Download the raw daily series: strands-agents.csv

Gid Score breakdown

Adoption88
Community40
Attention0
Momentum52

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 17, 2026Nov 19, 06:24 UTC
GitHub starsNov 19, 2026Nov 19, 06:26 UTC
Hacker News mentionsNov 18, 2026Nov 19, 06:26 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

Strands Agents FAQ

How much does Strands Agents cost?

Strands Agents is open source and free to use; you pay only for the models and infrastructure it runs on.

Is Strands Agents open source?

Yes. Strands Agents is open source, released under the Apache-2.0 license.

How popular is Strands Agents?

Strands Agents was downloaded 9M times from PyPI in the week ending Nov 17, 2026, up 1.3% on the week before and up 3.8% over the last 30 days compared with the 30 before. The GitHub repository has 9,252 stars, 405 of them added in the last 30 days. The latest stable release is 1.65.0, published Nov 13, 2026; there were 22 stable releases in the past 30 days.

What is the latest version of Strands Agents?

The latest stable release we track is 1.65.0, published on Nov 13, 2026.

What are the alternatives to Strands Agents?

The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.

For the makers of Strands Agents badges, corrections

Add a live badge to your README or site:

AgentGid: #10 in Frameworks Gid Score: 56/100 downloads: 9M/week ▲4% 30d

[![AgentGid: #10 in Frameworks](https://agentgid.com/badges/strands-agents-rank.svg)](https://agentgid.com/agents/strands-agents/)
[![Gid Score: 56/100](https://agentgid.com/badges/strands-agents-score.svg)](https://agentgid.com/agents/strands-agents/)
[![downloads: 9M/week ▲4% 30d](https://agentgid.com/badges/strands-agents-downloads.svg)](https://agentgid.com/agents/strands-agents/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

PyPI: strands-agents. GitHub: strands-agents/harness-sdk. See data sources for how each one is collected.