Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that ke…

A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confidence on every decision.

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

Control and execution plane for AWS Lambda MicroVMs: build images, launch Firecracker microVMs, scale fleets inside your quotas, call into them securely, watch it all live.

Reproducible benchmark comparing full catalog context with metadata-filtered semantic retrieval using Amazon S3 Vectors and Bedrock.

Deploy any web app to an AWS Lambda MicroVM with public CloudFront access. One command.

Strands Agents-powered, Amazon Nova LLM-driven Mars Curiosity Rover Agent. Natural-language control of a NASA Curiosity rover & AWS DeepRacer — multi-runtime (ROS2 / rosbridge / HTTP), autonomous N…

Simulated environments for robot agent evaluation and reinforcement learning.

AWS DeepRacer Simulation and Training Container

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Ship faster with parallel Claude Code sessions — one native macOS window, git worktrees, sandboxes, auto-resume, merge & finish, token dashboard.

Python functions powered by AI agents - with runtime post-conditions for reliable agentic workflows.

Train the smallest LM you can that fits in 16MB. Best model wins!

Toolkit for Seamlessly Enabling RL Training on Any Agent with Bedrock AgentCore.

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

Convert OpenClaw skills (markdown documentation) to executable Strands Agents tools

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

Privacy-first voice dictation for macOS — powered by on-device Whisper AI. No cloud, no tracking.

Autonomous experiment loop extension for pi

Build Real-Time Knowledge Graphs for AI Agents

Control robots and physical hardware with natural language through Strands Agents.

This python package rewrite to support the new version Deepracer Console Software version 1.0.606.0

True async agentic tools — the model keeps talking while tools run in the background

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

A simple realtime 3D object renderer for humans ✨

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents

Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment.