rogeriochaves

rogeriochaves / open-managed-agents

Public

Self-hostable, open-source alternative to Claude Managed Agents. Multi-LLM support (Anthropic, OpenAI, Ollama), enterprise governance (org/teams/RBAC)

13
4
100% credibility
Found Apr 15, 2026 at 13 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Open Managed Agents is an open-source, self-hosted platform for creating, running, and governing AI agents compatible with multiple language models.

How It Works

1
🚀 Launch your AI hub

Download the free tool and start it on your computer with one simple command – no setup hassle.

2
🔐 Sign in easily

Log in with the ready-made admin account to access your personal dashboard.

3
Build your first helper
📋
Ready templates

Choose a pre-made assistant for support, research, or analysis.

💭
Chat to create

Tell it in plain words what you want, and it builds it step by step.

4
✨ Your assistant is ready

Click create, and your new AI helper appears in your list, fully set up.

5
🛠️ Set up its workspace

Pick a safe space with internet access or limits, and add any special tools.

6
🗣️ Start chatting

Send a message to your assistant and watch it think, use tools, and reply live.

🎉 AI agents at work

Your self-hosted helpers run securely on your own setup, saving data and costs.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 13 to 13 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is open-managed-agents?

Open Managed Agents is a self-hostable, open-source alternative to Anthropic's Claude Managed Agents, written in TypeScript. It provides a full platform for building, running, and managing AI agents with multi-LLM support for Anthropic, OpenAI, Ollama, and more, deployable via Docker Compose or Helm charts. Users get a web UI for quickstarts and templates, a CLI for scripting, real-time session streaming, and enterprise governance like org/teams/RBAC, encrypted vaults, and audit logs—all on your infrastructure.

Why is it gaining traction?

It breaks free from Claude's cloud-only limits, letting teams mix providers (local Ollama for air-gapped setups, OpenAI for scale) while matching the same builder, templates, and 1:1 API. Self-hostable GitHub deploys with JSON governance configs appeal to ops-heavy teams, and built-in MCP connectors for Slack, GitHub, Notion add instant value without custom glue code.

Who should use this?

Platform teams sharing agent runtimes across engineering orgs, enterprises enforcing "no data leaves" policies with RBAC and budgets, or AI devs prototyping local models via Ollama without vendor bills. Perfect for compliance-driven support agents or incident responders needing governance.

Verdict

Solid pick for self-hostable agents despite 13 stars and 1.0% credibility—387 tests, polished docs, and Helm charts show real maturity. Early stage means monitor for adoption, but deploy now if Claude lock-in bugs you.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.