# Strands Agents > Strands Agents is AWS's open-source agent SDK for Python and TypeScript. A model-driven loop runs tools, MCP servers, multi-agent patterns, sessions, interrupts for human approval and OpenTelemetry tracing, with Amazon Bedrock as the default model provider. - Canonical: https://www.anchorterminal.com/tools/strands-agents - Pricing: https://www.anchorterminal.com/tools/strands-agents#pricing - Reviews: https://www.anchorterminal.com/tools/strands-agents#reviews - Markdown: https://www.anchorterminal.com/tools/strands-agents.md (~6,050 tokens) - Slim: https://www.anchorterminal.com/tools/strands-agents.min.md (~1,430 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/strands-agents.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT strands-agents.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-07 ## Overview **Grade A · 80/100 · rank #15 of 1486 · #4 in Agent frameworks & SDKs · agent-ready · confidence medium** More from Amazon Web Services, listed separately because each is its own product: [Strands Decider 2B](https://www.anchorterminal.com/tools/strands-decider.md) (Decision models). ## Assessment An Apache-2.0 agent SDK for Python and TypeScript with a managed MCP client, multi-agent patterns, interrupts and Cedar policies for approval, opt-in OpenTelemetry and no usage analytics. Bedrock is the default model, the default sandbox is the local host, and three session-isolation advisories were fixed in October 2026. ## Facts | Field | Value | | --- | --- | | Vendor | Amazon Web Services (https://strandsagents.com) | | Kind | Agent framework | | Category | Agent frameworks & SDKs (https://www.anchorterminal.com/categories/frameworks) | | Auth | None · A library with no credentials of its own. The default Bedrock provider uses the caller's AWS credentials; other providers take their own API keys. | | Pricing | Free (Free · OSS) · Free and open source under Apache-2.0. You pay for model calls, on Bedrock by default or with any supported provider. | | x402 | No · No x402, MPP or L402 in the docs or the repository (checked 2026-11-06). | | Licence | Apache-2.0 | | Packages | pypi: `strands-agents`; npm: `@strands-agents/sdk`; pypi: `strands-agents-tools` | | Source | https://github.com/strands-agents/harness-sdk | | Docs | https://strandsagents.com/docs | | llms.txt | https://strandsagents.com/llms.txt | | Last release | 2026-11-04 | | GitHub stars | 9,066 (as of 2026-11-06) | | npm downloads / week | 697,548 | | PyPI downloads / week | 8,902,370 | | Surface listed | The Strands Agents SDK for Python and TypeScript, read from the strands-agents/harness-sdk repository (docs source, workflows, SECURITY.md, tags), strandsagents.com/llms.txt, OSV and the npm registry on 6 November 2026. Nothing was installed | | Scope | The SDK. Strands Decider 2B, a decision model from Strands Labs, has its own Anchor Terminal listing. The repository also holds the Strands harness, a ready-made agent built on the SDK, a CLI and an MCP server for the docs | | Languages | Python 3.10 or newer, and TypeScript on Node 22 or newer | | Models | Amazon Bedrock by default, plus Anthropic, OpenAI, Google, Ollama and other providers through the same agent code | | MCP client | MCPClient over stdio, Streamable HTTP and SSE, passed straight to `Agent(tools=[...])` with its lifecycle managed | | Multi-agent | Agents as tools, swarms, graphs, workflows and A2A | | Human approval | Interrupts from hooks or tools pause a run for a response; the harness gates tool calls with ask or smart presets, natural-language rules or Cedar policies | | Sandbox | File and shell tools route through a sandbox seam that defaults to the local host, with Docker and SSH sandboxes as options | | Telemetry | None found by default. OpenTelemetry traces, metrics and logs once configured | | Versioning | Semantic versioning with experimental APIs under strands.experimental, deprecation warnings and removal at the next major | | Capabilities | agent.framework, agent.mcp-client, agent.multi-agent, agent.durable | | Tags | framework, python, typescript, open-source, llms-txt, mcp, otel, a2a, aws | | JSON | https://www.anchorterminal.com/api/v1/tools/strands-agents.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-11-06 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 87 | 17.4 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 95 | 15.4 | | Agent ergonomics | 13% | 16.2 | 87 | 14.1 | | Security & auth | 14% | 17.5 | 89 | 15.6 | | Payments & pricing | 10% | 12.5 | 60 | 7.5 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 87 | 7.6 | | Transparency & trust (editorial 86, provenance 58) | 7% | 8.8 | 72 | 6.3 | | Negative events | up to −15 | up to −15 | 2026-10-23 and 2026-10-27. Three GitHub advisories for strands-agents. GHSA-4v6f-7vjh-6x4m (high) says the A2A server shared conversation history across callers with different context IDs, fixed in Python 1.43.0 and TypeScript 1.5.0. GHSA-3w55-933p-8pv5 (high) and GHSA-763v-5pjm-fx36 (moderate) say the default FileSessionManager stored sessions in a world-readable /tmp path that followed symlinks, fixed in 1.48.0. All published with fixes and credited, so 4 points. https://github.com/strands-agents/harness-sdk/security/advisories/GHSA-3w55-933p-8pv5 | -4 | | **Total** | | | | **80 → A** | ### Why each score - Reliability 87 (checked 2026-11-06): Local-package reading. Official PyPI and npm packages with Python 3.10 and Node 22 stated (20). A public CI workflow runs lint, type checks, unit and integration tests for each package on pull requests to main, plus security-audit workflows, and the latest Python, TypeScript, harness and MCP runs on main passed on 6 November (25). 664 open issues and 1,151 open issues and pull requests on 6 November, with 545 issues opened in the 90 days to 3 November. Of the 50 newest, 12 had a comment and 15 were closed, and 9 of the 40 newest open items carry a bug label. An issue-responder workflow runs on new issues (12). A written semantic versioning policy, experimental APIs kept apart, and deprecations removed only at a major (15). 1.0 since 15 July 2025 (15). 20+25+12+15+15 = 87. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 95 (checked 2026-11-06): Framework reading. Typed Python and TypeScript APIs with a reference for each (25). llms.txt with a Markdown twin of every page (10). The llms.txt and docs say when to use Strands over a hand-written loop and when to take the harness rather than the SDK (18). Tools are typed from decorated functions or Zod schemas (15). Python and TypeScript examples on every page, stop reasons and hook events documented, with no catalogue of exceptions (12). Versioning page and tagged releases per package (15). 25+10+18+15+12+15 = 95. - Agent ergonomics 87 (checked 2026-11-06): Framework reading. An MCPClient is passed straight to the agent in a few lines and its lifecycle is managed, with tool filtering per client (22). Conversation managers, turn limits, token budgets and cancellation bound each run (20). Stop reasons and typed events, and hooks that can retry a model or tool call (16). Retry strategies, session managers that persist and resume a conversation, and interrupts that resume where they paused (17). Two official languages, but the default provider is Bedrock, which needs AWS credentials and model access (12). 22+20+16+17+12 = 87. - Security & auth 89 (checked 2026-11-06): Framework reading (telemetry defaults, approvals, guardrails, sandboxing). No usage analytics found in either SDK, and OpenTelemetry is opt-in (25). Interrupts and the harness's interventions gate tool calls behind human approval or Cedar policies, but the default sandbox is the local host (16). Guardrails, PII redaction and trusted message history pages, with Bedrock Guardrails integration (13). OpenTelemetry traces for every model and tool call (15). The AWS Vulnerability Disclosure Program on HackerOne and three advisories in October 2026 published with fixed versions (20). 25+16+13+15+20 = 89. - Payments & pricing 60 (checked 2026-11-06): Self-hosted rule. Free Apache-2.0 packages with nothing to buy from the project (20 + 20 + 20). No payment protocol (0). Model calls are paid to the provider. 0+20+20+20 = 60. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 87 (checked 2026-11-06): Python 1.64.0 and TypeScript 1.24.0 tagged on 4 November 2026 (30). Python 1.55.0 on 8 September, 1.61.0 on 14 October, 1.62.0 on 21 October and 1.63.0 on 30 October among many releases in 90 days (20). 664 open issues and 1,151 open issues and pull requests on 6 November, with 545 issues opened in the 90 days to 3 November. Of the 50 newest, 12 had a comment and 15 were closed, and 9 of the 40 newest open items carry a bug label. An issue-responder workflow runs on new issues (12). Both official SDKs are current (15). Dependency floors, security-audit workflows and CI passing on main (10). 30+20+12+15+10 = 87. - Transparency & trust 72 (checked 2026-11-06): Apache-2.0 (30). A library that stores session state where the developer configures it. The default FileSessionManager kept sessions world-readable in /tmp until 1.48.0, which the October advisories record and fix (20). A written deprecation policy with warnings and removal at majors, without a dated support window (16). Telemetry is opt-in and documented (20). 30+20+16+20 = 86. Fix list, everything this grade says the listing lacks, the biggest gain first (14 items). What it covers is at https://www.anchorterminal.com/fixes/strands-agents.md (JSON https://www.anchorterminal.com/fixes/strands-agents.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{"listing": "strands-agents", "plan": "read"}`, free while the beta runs ### What we couldn't check - Reply times were sampled from comment counts on the 50 newest issues, not read issue by issue - PyPI's project pages answered a bot check, so release dates come from the repository's tags ### Sources - repository (docs source, workflows, SECURITY.md, tags): (seen 2026-11-06) - llms.txt: (seen 2026-11-06) - versioning and support policy: (seen 2026-11-06) - MCP tools: (seen 2026-11-06) - traces: (seen 2026-11-06) - harness interventions: (seen 2026-11-06) - GHSA-4v6f-7vjh-6x4m: (seen 2026-11-06) - GHSA-3w55-933p-8pv5: (seen 2026-11-06) - npm @strands-agents/sdk: (seen 2026-11-06) - PyPI downloads: (seen 2026-11-06) - GitHub API, repository, issues and Actions runs: (seen 2026-11-06) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/strands-agents/history.json - 2026-11-06: graded 80 A (methodology 0.7) ## Who's behind it (provenance 58/100, checked 2026-11-06) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Amazon Web Services, Inc. | 20/20 | | Domain age | strandsagents.com, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | no hosted endpoint | n/a | | Terms of service | nothing hosted, so the Apache-2.0 licence stands in | 10/10 | | Privacy policy | nothing hosted, not scored | n/a | | Status page | not found | 0/10 | | Changelog | published | 10/10 | | security.txt | not found | 0/10 | | People named | 4 named with their role, none with a public profile | 7/10 | | Support route | help pages, a community | 5/5 | The licence file and NOTICE attribute the project to Amazon.com, Inc. or its affiliates; SECURITY.md sends reports to the AWS Vulnerability Disclosure Program on HackerOne. strandsagents.com/robots.txt allows all crawlers with Content-Signal ai-train=no, search=yes, ai-input=yes. strandsagents.com/.well-known/security.txt returns 404. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The Apache-2.0 licence stands in and the check scores in full. **Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored. ## Humans behind the project (researched 2026-11-06 from public pages, not part of the grade) ### Key people - Jeff Bezos, Founder and executive chairman, Amazon - Andy Jassy, President and CEO, Amazon - Matt Garman, CEO, Amazon Web Services - Werner Vogels, CTO, Amazon - Note: AWS is a subsidiary of Amazon; Amazon's founder is shown as founder. Matt Garman (AWS CEO) and Andy Jassy (Amazon CEO) are named in their roles on aboutamazon.com articles from 2026; Jeff Bezos's and Werner Vogels's roles come from their Wikipedia articles, read 28 October 2026. Product people named on single listings are left as they are. Copied from the Strands Decider 2B listing (checked 28 October 2026) for the Strands Agents SDK on 6 November 2026; the company facts are AWS's, and no SDK maintainer was added. ### Ownership and investors - Ownership: Part of Amazon.com, Inc. ### Getting support - Discord: https://discord.gg/strands - Help: https://console.aws.amazon.com/support/home#/case/create?issueType=technical - Help: https://console.aws.amazon.com/support/home#/case/create?issueType=customer-service - Sources: https://aws.amazon.com/contact-us/, https://strandsagents.com/, https://en.wikipedia.org/wiki/Amazon_(company), https://en.wikipedia.org/wiki/Jeff_Bezos, https://en.wikipedia.org/wiki/Amazon_Web_Services ## Live (updated 2026-11-07 16:00 UTC) - github `strands-agents/harness-sdk` typescript/v1.24.0, released 2026-11-04 - npm `@strands-agents/sdk` 1.24.0 - pypi `strands-agents` 1.64.0, released 2026-11-04 - pypi `strands-agents-tools` 0.9.0, released 2026-11-04 - security.txt: none - Always current: https://www.anchorterminal.com/api/v1/live/strands-agents.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Strengths - No usage analytics found, with OpenTelemetry tracing opt-in - Interrupts and interventions pause tool calls for human approval or a Cedar policy - MCP servers passed straight to the agent, with lifecycle handled - Python and TypeScript SDKs released weekly, 1.0 since July 2025, under a written versioning policy - llms.txt with a Markdown twin of every docs page ## Weaknesses - Three advisories in October 2026 on A2A session sharing and world-readable default session files, fixed in 1.43.0 and 1.48.0 - The default sandbox for shell and file tools is the local host - Bedrock is the default provider, so a bare agent needs AWS credentials and model access - Experimental modules and fast-moving standards (MCP, A2A, OTel conventions) sit outside the semantic versioning guarantee ## Before you call it (notes for agents) 1. Upgrade to strands-agents 1.48.0 or later, and set a private session directory rather than the /tmp default 2. Pass a model explicitly when AWS credentials aren't configured, since Bedrock is the default 3. Use interrupts or the harness's `interventions` for tools that write, send or pay 4. Run shell and file tools in the Docker or SSH sandbox when the agent runs untrusted code 5. Pin a minor version when using A2A, MCP or experimental modules ## Get started Install: ```bash pip install strands-agents strands-agents-tools # TypeScript: npm i @strands-agents/sdk ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | AI SDK | AA | 89.8 | 1 | agent.framework, agent.mcp-client, agent.multi-agent, agent.durable | no | https://www.anchorterminal.com/tools/vercel-ai-sdk.md | | OpenAI Agents SDK | AA | 86.2 | 3 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/openai-agents-sdk.md | | Pydantic AI | A | 81.9 | 7 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/pydantic-ai.md | | Microsoft Agent Framework | A | 79.4 | 18 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | no | https://www.anchorterminal.com/tools/microsoft-agent-framework.md | | Mastra | BB | 74.2 | 91 | agent.framework, agent.durable, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/mastra.md | | Docker Agent | BB | 73.6 | 101 | agent.framework, agent.multi-agent, agent.mcp-client, agent.durable | no | https://www.anchorterminal.com/tools/docker-agent.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - Python strands-agents 1.64.0 and TypeScript @strands-agents/sdk 1.24.0 tagged on 4 November 2026 in the strands-agents/harness-sdk monorepo, which now holds both SDKs, the Strands harness, a CLI and an MCP server; the TypeScript repository was archived on 2 June 2026 (source: ) - v0.1.0 tagged on 16 May 2025 and v1.0.0 on 15 July 2025 (source: ) - Three advisories in October 2026, all fixed. The A2A server shared conversation history across callers (GHSA-4v6f-7vjh-6x4m, high, fixed in Python 1.43.0 and TypeScript 1.5.0), and the default FileSessionManager in /tmp was world-readable and followed symlinks (GHSA-763v-5pjm-fx36 and GHSA-3w55-933p-8pv5, fixed in 1.48.0) (source: ) - OpenTelemetry tracing is opt-in through the `otel` extra and StrandsTelemetry; no usage analytics were found in the Python or TypeScript source (source: ) - MAL-2026-904 flags strands-agents-anthropic on PyPI as a probable pentest package that sends basic host data; it isn't published by the Strands project (source: ) - #4 of 20 in Best agent frameworks and SDKs: https://www.anchorterminal.com/best/frameworks/index.md - All 171 frameworks comparisons: https://www.anchorterminal.com/compare/frameworks/index.md ## Compare - [AgentOS vs Strands Agents](https://www.anchorterminal.com/compare/agentos-vs-strands-agents.md): BB 75.8 vs A 80 - [Agno vs Strands Agents](https://www.anchorterminal.com/compare/agno-vs-strands-agents.md): BB 70.9 vs A 80 - [BoxLang AI vs Strands Agents](https://www.anchorterminal.com/compare/boxlang-ai-vs-strands-agents.md): B 65.8 vs A 80 - [Claude Agent SDK vs Strands Agents](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-strands-agents.md): BB 70.3 vs A 80 - [CrewAI vs Strands Agents](https://www.anchorterminal.com/compare/crewai-vs-strands-agents.md): C 59 vs A 80 - [Cursor Agent SDK vs Strands Agents](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-strands-agents.md): B 63.7 vs A 80 - [Docker Agent vs Strands Agents](https://www.anchorterminal.com/compare/docker-agent-vs-strands-agents.md): BB 73.6 vs A 80 - [Agent Development Kit (ADK) vs Strands Agents](https://www.anchorterminal.com/compare/google-adk-vs-strands-agents.md): B 68.7 vs A 80 - [guilds.run vs Strands Agents](https://www.anchorterminal.com/compare/guilds-run-vs-strands-agents.md): D 53.4 vs A 80 - [LangGraph vs Strands Agents](https://www.anchorterminal.com/compare/langgraph-vs-strands-agents.md): B 69.8 vs A 80 - [LlamaIndex Framework vs Strands Agents](https://www.anchorterminal.com/compare/llamaindex-vs-strands-agents.md): BB 70 vs A 80 - [Mastra vs Strands Agents](https://www.anchorterminal.com/compare/mastra-vs-strands-agents.md): BB 74.2 vs A 80 - [Microsoft Agent Framework vs Strands Agents](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-strands-agents.md): A 79.4 vs A 80 - [OpenAI Agents SDK vs Strands Agents](https://www.anchorterminal.com/compare/openai-agents-sdk-vs-strands-agents.md): AA 86.2 vs A 80 - [Pydantic AI vs Strands Agents](https://www.anchorterminal.com/compare/pydantic-ai-vs-strands-agents.md): A 81.9 vs A 80 - [smolagents vs Strands Agents](https://www.anchorterminal.com/compare/smolagents-vs-strands-agents.md): C 58.7 vs A 80 - [Strands Agents vs TradingAgents](https://www.anchorterminal.com/compare/strands-agents-vs-tradingagents.md): A 80 vs C 61.4 - [Strands Agents vs AI SDK](https://www.anchorterminal.com/compare/strands-agents-vs-vercel-ai-sdk.md): A 80 vs AA 89.8 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on strandsagents.com or one of its subdomains, or the README at the root of github.com/strands-agents/harness-sdk. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "strands-agents", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Strands Agents on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Strands Agents on Anchor Terminal](https://www.anchorterminal.com/badges/strands-agents.svg)](https://www.anchorterminal.com/tools/strands-agents) ``` Plain link: ```html Strands Agents on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Strands Agents is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/strands-agents-dark.png - Light: https://www.anchorterminal.com/assets/share/strands-agents-light.png --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp