Strands Agents
Open source sandbox and toolkit for building production AI agents
Visit strandsagents.com ↗What is Strands Agents?
Strands is an open source toolkit for constructing production AI agents in Python and TypeScript. It provides a fully assembled agent harness, harness SDK for custom builds, sandboxed execution environment (Box), virtual shell, evaluation tools, and experimental labs. Box combines OS-level isolation with Dogwood policy language to control agent access and actions. The toolkit includes built-in tools for shell operations, file access, web requests, and MCP server integration, plus production deployment guides for AWS Lambda, Fargate, EKS, and Docker.
Designed for developers building AI agents at scale. Includes session persistence, long-term memory, multi-agent coordination, observability features, and responsible AI guardrails. Currently supports local execution on macOS with Apple silicon, in preview.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Strands Agents automatically. Evidence: Trending on git-trends.github.io: agent files (claude-code) in strands-agents/box. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces

Manage teams of AI agents to run your business from one dashboard

Persistent memory for AI agents across Claude Code, Cursor, and MCP clients