No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by open-ma · Agent Tool · ★ 169
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is open-managed-agents safe to install? View the security audit →
Open Managed Agents Open-source alternative to Claude Managed Agents — a meta-harness for AI agents you can run yourself. 🌐 openma.dev · 📖 docs.openma.dev · 💬 github.com/open-ma/open-managed-agents Write a harness. Deploy. The platform runs it — with sessions, sandboxes, tools, memory, vaults, and crash recovery out of the box. Drop-in compatible with the Claude Managed Agents API; runs on Cloudflare Workers + Durable Objects, or on your own box. Two ways to run OMA The same harness, business logic, and event-log model run on both. Pick the one that matches your hosting story:
| Stars | 169 |
| Forks | 12 |
| Language | TypeScript |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 70.3631726762833/100 |
| Open Issues | 18 |
| Last Updated | 2026-06-02 |
| Created | 2026-04-10 |
| Platforms | claude-code, node |
| Est. Tokens | ~649k |
Looking for a open-managed-agents alternative? If you're comparing open-managed-agents with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open Managed Agents — an open-source alternative to Claude Managed Agents and OpenAI Agents API. Deploy with N
OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable stat
Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops
The agentic company OS. The brains of your company, built on Claude Code and Codex, working on your Anthropic
Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat
Explore other popular agent tool tools:
open-managed-agents is openma - open-source, self-hosted implementation of Claude's Managed Agents API. Drop-in compatible. Runs on Cloudflare Workers + Durable Objects or Node.js. Apache 2.0.. It is categorized as a Agent Tool with 169 GitHub stars.
open-managed-agents is primarily written in TypeScript. It covers topics such as acp, agent-framework, agent-infrastructure.
You can find installation instructions and usage details in the open-managed-agents GitHub repository at github.com/open-ma/open-managed-agents. The project has 169 stars and 12 forks, indicating an active community.
open-managed-agents is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to open-managed-agents on Agent Skills Hub include open-managed-agents, openhermit, platform. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: