ByteZone
Back to listClaim this project

omnigent-aiAI apps

omnigent

An open-source orchestration layer for running, switching, and collaborating across multiple AI agents through terminal, web, desktop, and cloud-sandbox sessions.

  • Backend
  • Full stack
  • DevOps
  • AI coding
  • Collaboration
  • Security
  • CLI
  • Web
  • Desktop
  • Windows
  • macOS
  • Linux
  • Browser
  • Self-hostable
  • Runs locally
  • Docker supported
Open websiteView on GitHub
omnigent screenshot
Popularity
9.8k Stars
GitHub stars
Recent activity
9/9/2026
Updated in the last 30 days
License
APACHE-2.0
Permissive

Why it matters

We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.

Last 90 days

Problem

Addresses the fragmentation of AI agent tools, where users struggle to manage workflows consistently across disparate platforms and models.

Practical value

Provides cross-device session synchronization, multi-agent orchestration, and cloud sandbox execution, significantly reducing the maintenance overhead for complex agent tasks.

Innovation / differentiation

Acts as a meta-orchestration layer that unifies various mainstream agent frameworks through a common interface, introducing policy-based governance that differentiates it from standard tools.

Leverage potential

Enables developers to build portable and auditable automation systems by defining agent behaviors via YAML and supporting diverse cloud sandbox providers.

Why now

The AI agent ecosystem is currently transitioning from single-purpose tools to complex systems, making this project timely for addressing the urgent need for multi-agent collaboration and governance.

Community activity

In the last 90 days there were 1433 new issues and 5350 pull requests; the bounded issue/PR samples include 60 issue authors and 36 PR contributors, with 14 releases.

Maintainer responsiveness

The 100-issue window sample had a 81% close rate, and the 100-pull-request sample had a 81% merge rate. Maintainer-response observations covered 36% of that issue sample, with a 6% response rate and median first response of 4.4 hours.

36 contributors in PR sample14 releasesIssue response rate 6% · sample 36 (36% coverage)Median first response 4.4hPR merge rate 81% · 100 sampled in window

Key highlights

  • Run Claude Code, Codex, Cursor, and other agents in shared sessions
  • Keep session state synchronized across terminal, web, and desktop collaboration surfaces
  • Deploy the server with Docker and run sessions in multiple cloud sandbox providers

Quick start

How it is installed, how hard it is, and where to start.

Where it runs

Runs locally

Difficulty

Harder — CLI / server skills help

Docker supportedSelf-hostableRuns locally
  1. 01Use the official installer on Linux/macOS or uv tool install omnigent; on native Windows, follow the README’s uv installation path.
  2. 02Run omnigent setup to configure an existing model subscription, API key, or compatible gateway, then validate one local session and its permissions first.
  3. 03Only when team or remote access is needed, enable the server, authentication, Docker/cloud sandboxes, and add approval and budget policies incrementally.

Best for

  • Teams that want data on their own servers
  • Developers who want to try it on their machine
  • People who prefer Docker deploys

More about it

Omnigent puts Claude Code, Codex, Cursor, OpenCode, Hermes, Pi, and custom agents behind a shared session and policy layer. Tasks can start in the terminal and continue in the web or desktop interface, while server deployments and several cloud sandbox providers support remote execution. It also includes team sharing, session forks, approval policies, tool-call limits, and cost caps. Native Windows support is explicitly degraded: the server and SDK-based harnesses work, but the stronger filesystem and network sandboxing available on Linux and macOS is not present.

Sources

Each field shows its status and source — expand to review.

15 · Expand

  • capability tags

    Verified

    ai_coding, collaboration, security

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

  • editor note

    Verified

    {"en":"This is closer to an agent runtime and collaboration layer than a single chat client, making it most relevant to teams already using several agents. Its deployment and permission surface is broad, so start with a local, least-privilege setup before production use.","zh":"更像“Agent 运行与协作底座”而不是单一聊天客户端，适合已经同时使用多个 Agent 的团队。部署和权限面较宽，上生产前应先从单机、小权限策略开始。"}

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

  • how to use

    Verified

    {"steps":[{"en":"Use the official installer on Linux/macOS or `uv tool install omnigent`; on native Windows, follow the README’s uv installation path.","zh":"在 Linux/macOS 使用官方安装脚本，或用 `uv tool install omnigent`；Windows 原生环境按 README 使用 uv 安装。"},{"en":"Run `omnigent setup` to configure an existing model subscription, API key, or compatible gateway, then validate one local session and its permissions first.","zh":"运行 `omnigent setup` 配置已有模型订阅、API Key 或兼容网关，然后先启动一个本机会话验证 Agent 与权限。"},{"en":"Only when team or remote access is needed, enable the server, authentication, Docker/cloud sandboxes, and add approval and budget policies incrementally.","zh":"需要团队或远程使用时再启用服务器、认证、Docker/云沙箱，并逐层添加审批和预算策略。"}],"installAt":"local","difficulty":"hard"}

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

  • intro

    Verified

    {"en":"Omnigent puts Claude Code, Codex, Cursor, OpenCode, Hermes, Pi, and custom agents behind a shared session and policy layer. Tasks can start in the terminal and continue in the web or desktop interface, while server deployments and several cloud sandbox providers support remote execution. It also includes team sharing, session forks, approval policies, tool-call limits, and cost caps. Native Windows support is explicitly degraded: the server and SDK-based harnesses work, but the stronger filesystem and network sandboxing available on Linux and macOS is not present.","zh":"Omnigent 把 Claude Code、Codex、Cursor、OpenCode、Hermes、Pi 以及自定义 Agent 放到统一会话和策略层中。用户可以从终端启动任务，在 Web 或桌面界面继续查看，也可以把会话放到 Docker 部署的服务或多个云沙箱中运行。它还提供团队共享、会话分叉、审批策略、工具调用次数和成本限制。Windows 原生模式目前功能有明确降级：可运行服务器和 SDK 型 harness，但缺少 Linux/macOS 上完整的文件系统与网络沙箱。"}

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

  • Latest release

    Verified

    v0.12.0

    Source: GitHub API · latest_release=v0.12.0 · 9/9/2026

  • License

    Verified

    Apache-2.0

    Source: GitHub API · license.spdx_id=Apache-2.0 · 9/9/2026

  • needs api key

    Verified

    No

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

  • One-liner

    Verified

    {"en":"An open-source orchestration layer for running, switching, and collaborating across multiple AI agents through terminal, web, desktop, and cloud-sandbox sessions.","zh":"统一运行、切换和协作多个 AI Agent 的开源编排层，覆盖终端、Web、桌面与云沙箱会话。"}

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

  • Platforms

    Verified

    windows, macos, linux, browser

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

  • Category hint

    Inferred from materials

    ai-apps

    Source: Project README · hint=ai-apps · 8/14/2026

  • product forms

    Verified

    cli, web, desktop

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

  • role tags

    Verified

    backend, fullstack, devops

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

  • supports docker

    Verified

    Yes

    Source: Repository file · dockerfile=true; compose=true · 9/9/2026

  • supports local

    Verified

    Yes

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

  • supports self host

    Verified

    Yes

    Source: manual_curated · Manually curated from the verified project README; no in-app AI draft. · 8/17/2026

Related projects

Other verified projects matched by category, capabilities, and intended roles.

ouroboros

Ouroboros is an open-source, general-purpose AI agent with durable cross-restart memory that coordinates specialist swarms and rewrites its own implementation.

Same AI apps categoryBoth support AI coding

sutando

An open-source local AI agent that responds via voice and screen by day, and runs an autonomous build loop by night.

Same AI apps categoryBoth support AI coding

hermes-agent

A personal AI agent that runs locally or on remote infrastructure with terminal, messaging, memory, skills, and scheduled automation.

Same AI apps categoryBoth support AI coding

ollama

A local model runner for Windows, macOS, and Linux with a REST API plus Python and JavaScript clients.

Same AI apps categoryBoth support AI coding

unsloth

A desktop and developer toolkit for running, fine-tuning, and deploying language and diffusion models locally on Windows, macOS, and Linux.

Same AI apps categoryBoth support AI coding

Box

An advanced, fully offline on-device AI suite for Android supporting chat, image generation, and voice features.

Same AI apps categoryBoth support AI coding