Most teams embed AWS guidance directly into prompts or ad-hoc scripts, which increases context size and yields inconsistent agent behavior. Agent Plugins for AWS reframes that surface area as versioned, callable plugins—so coding agents can invoke repeatable AWS workflows (deploy, migrate, document, database patterns) without re-prompting best practices each time. The repo is geared toward developer-facing agent integrations (Claude Code, Codex, Cursor) and has been actively maintained by AWS Labs since early 2026 (repo created 2026-02-05, ~705 stars).
Agent Plugins for AWS
Equips AI coding agents with reusable AWS skills (deployment, serverless, Amplify, SageMaker) by packaging agent skills, MCP servers, hooks, and references so agents invoke vetted workflows instead of bloating prompts.
Introduction
Information
- Websitegithub.com
- AuthorsAWS Labs
- Published date2026/02/05
Categories
More Items
Turns fragile, implicit search progress into explicit, persistent, shared state for multi-agent information seeking — externalizes progress as Frontier Task, Evidence Graph, Coverage Map and Failure Memory, and uses pipeline-parallel scheduling plus a middleware harness to avoid repeated failed searches and improve utilization and throughput.
Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.
Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).