Show HN：Omnara – Claude Managed Agents 的开源替代方案

Hacker News (AI)

2026 年 10 月 22 日 00:44 · 约 8 分钟阅读

阅读语言

当前为来源原文，可切换为中文译文。

Show HN：Omnara – Claude Managed Agents 的开源替代方案 — 报道配图 · 来源：Hacker News (AI)

内容导读

Hey all, Kartik from Omnara ( https://omnara.com ) here. We're building an open-source API for running durable agents. You create an agent with an API call, and Omnara runs the agent loop, gives the agent sandboxes to run commands in, and handles secrets, permissions, and RBAC. Each agent's state is stored in Postgres, so agents survive restarts and cost nothing while idle. You can message them and stream their events over the API. You may remember us from our early days, when we made a remote-control phone app for Claude Code and Codex. Since the harness ran on a laptop back then, we had to build a relay to reach it, it stopped when the laptop closed, and moving it to a cloud sandbox meant syncing code and agent state between machines. We didn't think remote-controlling a local agent was end-game for how people would run agents, so we built a new product where the agent runs in the cloud, any client can talk to it through an API, and it can still use your laptop as one of its machines. Anthropic and OpenAI are building hosted versions of this, like Claude Managed Agents and the OpenAI Agents API. Omnara is an open-source version you can run on your own servers and use your own models. It's basically a harness server like the opencode or codex servers, but durable, scalable, with the usual harness features like file and shell tools, subagents, compaction, permission prompts, MCP, skills, memory, yada yada yada. Here's some interesting architectural decisions we made while building this out: Most harnesses, like Claude Code, Codex, OpenCode, Pi, Goose, etc, run the agent loop in one long-lived process that keeps its log in a JSONL or SQLite file. In Omnara, the log is an append-only event log in Postgres, with inputs, model outputs and tool calls stored as typed rows in their own tables. The loop runs on stateless workers in the control plane. A worker runs one iteration of the loop, either a model call or the tool calls it produced, then releases the agent and puts the next iteration on a queue in Postgres. Whichever worker is free picks it up, so each iteration of an agent's loop can run in a different process on a different machine. Each iteration's result commits in one transaction, so the model output, its tool calls, usage and the next wakeup are saved together or not at all. If a worker dies mid-iteration, nothing commits, its lease expires, and another worker retries it. Agents waiting on a user, a tool or a retry don't hold a worker, so one worker can multiplex thousands of agents. Also unlike other harnesses, the machines that the workers (our agent loop) run on aren't where the agent runs its commands. Instead, any macOS or Linux machine with an internet connection, like your laptop or any cloud sandbox, can run a small daemon (omnarad) that connects out to Omnara, so it doesn't need any open inbound ports. The agent then gets tools for that machine, like running a command or editing a file. An agent can have any number of machines connected to it. A fun thing I like to do is I have my laptop and a cloud sandbox connected to the same agent, so when my laptop is on, my agent codes there and I can interact with it, and I have it often push to Github. When I close my laptop, my agent sees the laptop went offline, pulls the latest changes to its cloud sandbox, and continues there. The entire codebase is open source at https://github.com/omnara-ai/omnara , and it’s self hostable, even on a single machine with docker compose. You can also use the hosted version at https://omnara.com . Let me know what you think! Comments URL: https://news.ycombinator.com/item?id=50183892 Points: 85 # Comments: 25

A self-hostable alternative to Claude Managed Agents and OpenAI's Agents API.

Website · Quickstart · Docs · API · Changelog · Discord

Omnara is an open-source managed agent platform. Use the API to run AI agents on any model and any machine, with tools, secrets, permissions, and streaming built in. Self-host it for free under Apache 2.0, or use Omnara Cloud .

Sign in at app.omnara.com . Your first project comes with a model provider ( omnara-openrouter ) and a pool of managed sandboxes ( default-pool ), so this config runs as is. Save it as agent.yaml :

version : v1 instruction : | You are an engineering assistant. Use your machine to run commands. model : provider_config : omnara-openrouter name : anthropic/claude-fable-5.1 machine_sources : - machine_pool_name : default-pool Launch it with the CLI (Node.js 22 or newer). If you're not logged in, the first command opens your browser to sign in.

npx omnara agents launch --file agent.yaml \ --name " Machine assistant " \ --message " Report this machine's operating system and free disk space. " Chat with the agent in your terminal with npx omnara agents chat , or open it in the dashboard to watch its tool calls and reply.

Create an API key in the dashboard and export it as OMNARA_TOKEN , install the SDK with npm install @omnara/sdk , and use the org and project IDs that npx omnara config prints:

import { readFile } from 'node:fs/promises' import { bearerToken , createOmnaraClient , openAgentEventStream , sdk } from '@omnara/sdk' const client = createOmnaraClient ( { auth : bearerToken ( process . env . OMNARA_TOKEN ! ) } ) const path = { orgID : 'org_...' , projectID : 'proj_...' } const config = await sdk . createAgentConfig ( { client , path , body : { source : await readFile ( 'agent.yaml' , 'utf8' ) , source_format : 'yaml' } , } ) const launched = await sdk . createAgent ( { client , path , body : { config : config . data . id , message : "Report this machine's free disk space." } , } ) const agentID = launched . data . agent . id for await ( const event of openAgentEventStream ( { client , path : { ... path , agentID } } ) ) { console . log ( event ) } The quickstart shows the same flow with the REST API.

To have your coding agent do the setup, give it this prompt:

Help me set up Omnara by following https://www.omnara.com/SKILL.md Self-host Requires Docker with Compose.

git clone https://github.com/omnara-ai/omnara.git cd omnara docker compose -f compose.yaml --profile app up -d Open http://localhost:8000 and sign up. Local development prints the verification link in docker compose logs api , so no email provider is needed. To build from source instead of using published images, run docker compose --profile app up -d --build .

A new instance has no models or machines yet. In the console, add a model provider and a model, connect this computer under Machines , and share both with your project. Sandboxes also work once your instance has a public URL .

npx omnara config --api-url http://localhost:8000/api/v1 --issuer-url http://localhost:8000 npx omnara login In agent.yaml , use your provider and model names, and replace the machine_pool_name entry with machine_name: . Then launch it with the same command as above.

The local defaults are intentionally insecure. For a real deployment, follow the self-hosting guide and the configuration reference .

Your product talks to Omnara, and Omnara runs each agent with the model, tools, and machines in its config.

flowchart TB subgraph yours["Your side"] users(["Your users"]) --> app["Your app REST API · TypeScript SDK"] team["Your team CLI · dashboard Slack · Discord · GitHub"] end subgraph omnara["Omnara"] api["API launch · input event stream · approvals"] pg[("Postgres each agent's event log")] worker["Workers run the agent loop"] end subgraph plug[" "] models["Models OpenAI · Anthropic OpenRouter · self-hosted"] tools["Tools built-in · skills MCP · custom"] machines["Machines sandboxes or your own laptop, VM, container"] end app --> api team --> api worker --> models worker --> tools worker --> machines classDef side fill:none,stroke:#8b949e,stroke-width:1px classDef core fill:#506FCF,stroke:#3D5BB5,stroke-width:1px,color:#ffffff classDef store fill:#3D5BB5,stroke:#2E4794,stroke-width:1px,color:#ffffff classDef plugin fill:none,stroke:#85A0E6,stroke-width:1.5px class users,app,team side class api,worker core class pg store class models,tools,machines plugin style yours fill:none,stroke:#8b949e,stroke-dasharray:4 3 style omnara fill:#506FCF14,stroke:#506FCF,stroke-width:1.5px style plug fill:none,stroke:#85A0E6,stroke-dasharray:4 3 linkStyle default stroke:#8b949e,stroke-width:1.5px Loading API. Your app, the CLI, and the dashboard all use the same REST API to launch agents, send messages, and answer approvals. Events stream back as they happen. Postgres. Every step of every agent is saved here. That record is the agent's state, so any worker can pick an agent back up after a crash or restart. Workers. Stateless processes that build the model context, call the model, and run tools. An agent only uses a worker while it's taking a turn, so one worker can serve many agents. Add workers to handle more turns at once. Machines. Each machine runs the omnarad daemon, which connects out to Omnara, so agents can run commands there without any inbound ports. Omnara also uses Redis, blob storage for attachments and tool outputs, and a memory filesystem. The architecture docs cover the details.

Claude Managed Agents and OpenAI's Agents API are hosted services for running agents on one company's models. Omnara does the same job as an open-source platform you can run anywhere, with any model.

Choose Claude Managed Agents or the Agents API if you use one company's models and want that company to run everything for you. Choose Omnara if you want to pick your models and machines, run the platform yourself, or keep agent data in your own database.

Each of these is an agent.yaml plus a SKILL.md in examples/ , and you can deploy any of them with one prompt to your coding agent.

There are also code samples for a CLI chat app built on the TypeScript SDK, custom tools over webhooks , and a SharePoint filesystem mount .

MCP server. Connect Claude Code, Codex, Cursor, or any MCP client that supports OAuth to https://app.omnara.com/mcp to launch and manage Omnara agents. You sign in through the browser, so there are no tokens to paste. In Claude, add it from the connectors directory . Omnara is also listed in the official MCP Registry as com.omnara/omnara .

claude mcp add --transport http omnara https://app.omnara.com/mcp codex mcp add omnara --url https://app.omnara.com/mcp Then sign in with /mcp in Claude Code or codex mcp login omnara in Codex. See Connecting MCP clients .

CLI. omnara manages agents, profiles, machines, model providers, secrets, skills, and cron triggers from your terminal or your coding agent's shell. Run npx omnara --help to start.

Setup skill. skills/setup-omnara-agent , also served at omnara.com/SKILL.md , walks a coding agent through setting up Omnara for your project.

What is Omnara? An open-source managed agent platform for running AI agents on any model and any machine.

How much does it cost? Nothing to self-host. Omnara Cloud has no platform fee. You can bring your own model keys and machines for free, or pay as you go for our models at provider token rates and our sandboxes by active time and retained storage. See pricing .

Can I self-host it? Yes. Run it with Docker Compose locally, then follow the self-hosting guide for production. The API, CLI, SDK, and config format are the same on Omnara Cloud and self-hosted deployments.

Which models work? Any model behind an OpenAI Responses, OpenAI Chat Completions, or Anthropic Messages compatible endpoint, including OpenAI, Anthropic, OpenRouter, Amazon Bedrock, LiteLLM, and Ollama.

Source development requires the Go version declared in go.mod , Node.js 24 or newer with Corepack, ripgrep, and Docker with Compose. Run the fast repository gate with make verify . See CONTRIBUTING.md for the full test suite, generated-code workflows, and pull request expectations.

READ THE ORIGINAL

阅读原始报道，获取完整语境。

本文内容来自 Hacker News (AI)，版权归原作者与发布方所有。

前往原始出处 ↗

SSCI 聚合公开资讯，内容以原始出处为准。反馈内容问题或申请更正

读者讨论

THE CONVERSATION

围绕事实与观点交流，尊重彼此。评论经审核后公开。

正在加载评论…

Show HN：Omnara – Claude Managed Agents 的开源替代方案

阅读原始报道，获取完整语境。

读者讨论

延伸阅读KEEP EXPLORING

情境感知人工智能的案例

Hugging Face 的全新 AI 生物学模型让你与 DNA 对话

人工智能的隐藏存储费用：推理留下了什么