Sandbox0 is the open-source sandbox for AI agents.

The future is Mythos-class agents that take vuln-to-exploits from days to hours, Linux defense is still stuck at human speed. Blacklight is the agentic counter-measure: a skills-native Managed Agent that directs OSS defensive primitives at the speed of the attack. GPL v2. (Opus 4.7 hackathon)

Claude Code skill for Anthropic Managed Agents — create / run / audit the cloud-hosted agent API end-to-end. 教 Claude 用 Anthropic 托管代理 API 的 skill,覆盖创建/运行/审计全流程。

Idiomatic Kotlin wrapper around com.anthropic:anthropic-java — suspend / Flow / sealed types over the official Anthropic Java SDK.

A web UI for Anthropic Managed Agents.

Multi-tenant IM gateway for AI agents. Scale users and agents many-to-many across channels.

Connect any messaging platform to Claude Managed Agents

Proxilion is the security layer for the agentic workforce. It turns managed AI agents into governed users by enforcing strict cryptographic boundaries on every API call to SaaS like Google Workspace, Salesforce, or Atlassian.

Autonomous AI agents built on Anthropic's Managed Agents API — on-call incident response, auto-fix PRs, Sentry triage, Jira sync, and Slack human-approval gates. Running 24/7 on a cron scheduler.

The Anthropic Provider enables Terraform to manage Anthropic Managed Agents, Skills, and Workspaces.

YUME: Anthropic "Built with Opus 4.7" Hackathon. AI social simulation where every resident is a Claude Managed Agent with persistent memory, living autonomously in a 3D city.

Production-ready agents, your way.

[BETA / POC] Unofficial Terraform provider for Anthropic Managed Agents API. Experimental, not production-ready, not affiliated with Anthropic.

FeedOracle × Claude Managed Agents — Compliance intelligence agent with 5 MCP servers (79 tools). MiCA, stablecoin risk, macro regime, agent governance.

An agronomist that watches, remembers, and calls you first. For smallholder farmers in Mozambique. Built with Claude Opus 4.7, Managed Agents, MCP, and Skills.

An open source alternative to OpenAI Workspace Agents and Claude managed agents. Setup and deploy 24/7 autonomous AI employees and agentic workflows.

AI prospect research agent using Anthropic Managed Agents API. Analyzes websites, generates branded HTML reports. Configurable for any industry.

A curated list of resources, tools, and community projects for Claude Managed Agents by Anthropic

Falsification-first biological law discovery — rejects 194 of 203 candidate laws, including its own.

Six Claude Opus 4.7 agents racing the bureaucracy clock when someone disappears. Built for Dominican Republic, designed to scale across Latin America. On Anthropic Managed Agents.