Run durable agents on your own servers with an open-source managed agent platform
Omnara is an open-source, self-hostable alternative to Claude Managed Agents and OpenAI's Agents API. You create an agent with an API call; Omnara runs the agent loop, gives it sandboxes to run commands in and keeps runs going.
Source
kmansm27 on Hacker News · 2026-10-21 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-22.
What they did
Omnara is an open-source, self-hostable alternative to Claude Managed Agents and OpenAI's Agents API. You create an agent with an API call; Omnara runs the agent loop, gives it sandboxes to run commands in and keeps runs going.
Result (as claimed)
Launched on Hacker News (90 points) as a way to run managed agents without a vendor lock-in.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude, ChatGPT, Docker. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Run durable agents on your own servers with an open-source managed agent platform What the original author did: Omnara is an open-source, self-hostable alternative to Claude Managed Agents and OpenAI's Agents API. You create an agent with an API call; Omnara runs the agent loop, gives it sandboxes to run commands in and keeps runs going. Reported result (as claimed by the author): Launched on Hacker News (90 points) as a way to run managed agents without a vendor lock-in. Source: https://news.ycombinator.com/item?id=50183892 Tools they used: Claude, ChatGPT, Docker Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Run durable agents on your own servers with an open-source managed agent platform What the original author did: Omnara is an open-source, self-hostable alternative to Claude Managed Agents and OpenAI's Agents API. You create an agent with an API call; Omnara runs the agent loop, gives it sandboxes to run commands in and keeps runs going. Reported result (as claimed by the author): Launched on Hacker News (90 points) as a way to run managed agents without a vendor lock-in. Source: https://news.ycombinator.com/item?id=50183892 Tools they used: Claude, ChatGPT, Docker Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Run durable agents on your own servers with an open-source managed agent platform What the original author did: Omnara is an open-source, self-hostable alternative to Claude Managed Agents and OpenAI's Agents API. You create an agent with an API call; Omnara runs the agent loop, gives it sandboxes to run commands in and keeps runs going. Reported result (as claimed by the author): Launched on Hacker News (90 points) as a way to run managed agents without a vendor lock-in. Source: https://news.ycombinator.com/item?id=50183892 Tools they used: Claude, ChatGPT, Docker Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to build your own coding agent or harness · How to run AI coding agents in a sandbox · How to self-host AI agents on a Raspberry Pi, Mac mini or homelab · How to use AI agents for Linux, servers and homelabs
Related use cases
Add an open memory layer so any agent remembers like ChatGPT
Open-sourced a memory layer so any AI agent can keep long-term context the way Claude.ai and ChatGPT do.
Let your agent run your newsletter through an open-source MCP
MailCheap, Marc Lou's open-source newsletter app, connects to Claude, ChatGPT and Grok Bot through MCP and to Claude Code, Codex and Cursor, so an agent can manage the list and send campaigns.
Add local-first memory to any LLM with Mnemo
Built Mnemo, a local-first AI memory layer for any LLM using Rust, SQLite and petgraph.
Make LLM agents team up in Pokemon Showdown battles
A researcher built a 2v2 Pokemon Showdown environment where two LLM agents must coordinate through team chat. You can watch battles with the chat shown, and the code is on GitHub.