Omnigent: declarative agent authoring and runtime framework
How to install omnigent?
omnigent-ai/omnigent
$git clone https://github.com/omnigent-ai/omnigentInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install omnigent by running `git clone https://github.com/omnigent-ai/omnigent`, then use it for the current task and follow its documentation at https://github.com/omnigent-ai/omnigent.
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 | # <img src="https://raw.githubusercontent.com/omnigent-ai/omnigent/main/docs/images/omnigent-logo.svg" alt="" height="38" valign="middle" /> Omnigent |
| 4 | |
| 5 | ### The open-source meta-harness for all your AI agents. |
| 6 | |
| 7 | Omnigent is an open-source **meta-harness** that gives you a common orchestration layer over Claude Code, Codex, Cursor, OpenCode, Hermes, Pi, and the agents you write yourself: swap or combine harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device — terminal, browser, phone, or the native desktop app. |
| 8 | |
| 9 | [](https://pypi.org/project/omnigent/) |
| 10 | [](https://github.com/omnigent-ai/omnigent/blob/main/LICENSE) |
| 11 | [](https://discord.gg/omnigent) |
| 12 |  |
| 13 | |
| 14 | [omnigent.ai](https://omnigent.ai) · **[⬇️ Download the macOS desktop app](https://omnigent.ai/download/mac)** |
| 15 | |
| 16 | </div> |
| 17 | |
| 18 | <p align="center"> |
| 19 | <img src="https://raw.githubusercontent.com/omnigent-ai/omnigent/main/docs/images/omnigent-desktop.png" alt="The Omnigent desktop app: starting a new session, with pinned and project-grouped sessions in the sidebar" width="720" /> |
| 20 | </p> |
| 21 | |
| 22 | --- |
| 23 | |
| 24 | ## Why Omnigent? |
| 25 | |
| 26 | Omnigent lets you: |
| 27 | |
| 28 | - **📱 Work with agents from any device, including your phone.** Sessions |
| 29 | follow you: start in your terminal, continue in the browser, pick it up on |
| 30 | your phone. Messages, sub-agents, terminals, and files stay in sync. |
| 31 | |
| 32 | - **🤖 Supervise multiple agents.** Mix Claude Code, Codex, Cursor, OpenCode, |
| 33 | Hermes, Pi, and custom agents (defined in YAML) together in the same |
| 34 | session. Ask one agent to review another's work, or split a task across |
| 35 | agents that are each good at different things. |
| 36 | |
| 37 | - **🔌 Use any model.** A first-party API key, a Claude/ChatGPT subscription, |
| 38 | or any compatible gateway. All first-class. |
| 39 | |
| 40 | - **🤝 Collaborate.** Share a session so teammates can chat with your agent |
| 41 | and watch it work live, co-drive it on your machine, or fork the |
| 42 | conversation to continue on their own. |
| 43 | |
| 44 | - **☁️ Run agents in cloud sandboxes.** No laptop required: run sessions in |
| 45 | disposable [Modal](https://modal.com), [Daytona](https://www.daytona.io), |
| 46 | [Islo](https://islo.dev), [E2B](https://e2b.dev), |
| 47 | [CoreWeave](https://docs.coreweave.com/products/sandboxes), |
| 48 | [Kubernetes](https://kubernetes.io), [OpenShell](https://github.com/NVIDIA/OpenShell), |
| 49 | [Boxlite](https://github.com/boxlite-ai/boxlite), or |
| 50 | [Databricks](https://www.databricks.com) sandboxes, launched from the |
| 51 | CLI or provisioned by the server per session (*managed hosts*). |
| 52 | |
| 53 | - **🛡️ Govern your agents.** Create |
| 54 | [policies](#6-govern-your-agents-with-policies) to pause for your approval |
| 55 | before risky actions, cap spend, or limit which tools an agent reaches. |
| 56 | They apply to the whole server, one agent, or a single chat. |
| 57 | |
| 58 | --- |
| 59 | |
| 60 | ## Quick start |
| 61 | |
| 62 | ### 1. Install |
| 63 | |
| 64 | One command installs Omnigent and everything it needs: |
| 65 | |
| 66 | ```bash |
| 67 | curl -fsSL https://raw.githubusercontent.com/omnigent-ai/omnigent/main/scripts/install_oss.sh | sh |
| 68 | ``` |
| 69 | |
| 70 | <details> |
| 71 | <summary>Optional integrations and extras</summary> |
| 72 | |
| 73 | Need an optional integration? Pass one or more extras to the installer: |
| 74 | |
| 75 | ```bash |
| 76 | curl -fsSL https://raw.githubusercontent.com/omnigent-ai/omnigent/main/scripts/install_oss.sh | sh -s -- --extra databricks |
| 77 | curl -fsSL https://raw.githubusercontent.com/omnigent-ai/omnigent/main/scripts/install_oss.sh | sh -s -- --extra modal,e2b |
| 78 | ``` |
| 79 | |
| 80 | Available user-facing extras include: |
| 81 | |
| 82 | - **Model providers:** `databricks`, `bedrock`, `vertex` |
| 83 | - **Sandbox providers:** `modal`, `daytona`, `boxlite`, `cwsandbox`, `e2b`, |
| 84 | `openshell`, `kubernetes` |
| 85 | - **SDK harnesses:** `antigravity`, `copilot`, `cursor`, `agents-sdk` |
| 86 | - **Storage and memory:** `s3`, `hindsight` |
| 87 | |
| 88 | </details> |
| 89 | |
| 90 | <details> |
| 91 | <summary>Pref |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
