# omnigent-ai/omnigent

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

Repository: https://github.com/omnigent-ai/omnigent
Canonical: https://ross.abutalabs.com/products/omnigent
Homepage: https://omnigent.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agents, ai, ai-agents, developer-tools, llm, ml, python, agent-framework, agent-governance, agent-orchestration, ai-agent, claude-code, codex, coding-agents, multi-agent, sandbox
Last push: 2026-08-27T00:03:42+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 5
- inputs: {"age_days": 83, "days_push": 7, "days_rel": 8, "gap_med": 6.0, "n_releases_24m": 13}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9314, forks 1432 (observed 2026-08-28T04:10:30.439339+00:00)

## What it is
Omnigent is an open-source meta-harness that provides a common orchestration layer over AI coding agents like Claude Code, Codex, Cursor, and custom YAML-defined agents. It adds sandboxing, stateful contextual policies, cloud sandbox hosting, and real-time multi-device collaboration on top of any agent harness.

## Use cases
- run claude code and codex through one unified interface
- supervise multiple ai coding agents in the same session
- enforce spend caps and approval gates on ai agents
- run coding agents in cloud sandboxes instead of my laptop
- check on long-running agent tasks from my phone
- share a live agent session with teammates for pair programming
- run agents unattended without exposing my credentials
- build custom multi-agent orchestrators in yaml

## When to choose
- you use multiple agent harnesses (Claude Code, Codex, Cursor, etc.) and want one orchestration, policy, and collaboration layer over all of them
- you need stateful guardrails like cost budgets, risk-based approval escalation, or model routing that static tool rules can't express
- you want to run agents unattended in OS-level or cloud sandboxes with filesystem, network, and credential isolation
- you want to start agent sessions in a terminal and continue them from a browser, phone, or desktop app with real-time sync

## When to avoid
- you need a battle-tested production tool - Omnigent is explicitly alpha with a pre-1.0 API
- you use a single agent harness and are happy with its native terminal UI and workflow
- you want a lightweight library to embed agent logic in your own code rather than a full platform with server, CLI, and apps
- you need Windows-native sandboxing - the OS sandbox relies on bubblewrap/seccomp (Linux) and Seatbelt (macOS)

## Facets
- artifact type: framework
- maturity: experimental
- function: agent-framework, security, middleware, web-framework, cli, chat-interface
- domain: large-language-models, developer-tools, security, self-hosted
- platform: python, windows, browser, cli, self-hosted, cross-platform
- tags: meta-harness, agent-orchestration, coding-agents, multi-agent, policies, sandboxing, cloud-sandboxes, real-time-collaboration, cost-control, credential-brokering, yaml-agents, harness-agnostic, sandbox, ai-agents, automation, macos, linux, ios, android, docker, kubernetes

## Member repositories
- omnigent-ai/omnigent (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:30.439339+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:22:30.583281+00:00, confidence not recorded.
  - readme: https://github.com/omnigent-ai/omnigent (fetched 2026-08-28T04:10:30.439339+00:00, sha 262d0855a18f)
  - homepage: https://omnigent.ai (fetched 2026-08-29T08:22:38.748995+00:00, sha 5ade6d5bf118)
  - site_page: https://omnigent.ai/quickstart/install (fetched 2026-08-29T08:22:38.758198+00:00, sha 9b6cff9b731c)
  - site_page: https://omnigent.ai/docs/use/coding-agents (fetched 2026-08-29T08:22:38.760409+00:00, sha 9ec28677acfc)
  - site_page: https://omnigent.ai/docs/interact/desktop (fetched 2026-08-29T08:22:38.764847+00:00, sha 6ed2ab10b724)
  - site_page: https://omnigent.ai/docs/interact/mobile (fetched 2026-08-29T08:22:38.766694+00:00, sha 9eedf1e9d769)
  - site_page: https://omnigent.ai/docs/use/builtin-agents (fetched 2026-08-29T08:22:38.768417+00:00, sha 2a4dd1a928e4)
  - site_page: https://omnigent.ai/docs/policies/overview (fetched 2026-08-29T08:22:38.770184+00:00, sha dad9fa1cda53)
  - site_page: https://omnigent.ai/docs/omnibox (fetched 2026-08-29T08:22:38.772002+00:00, sha cba2fcd720f7)
  - site_page: https://omnigent.ai/releases (fetched 2026-08-29T08:22:38.762396+00:00, sha f6043e537b9d)
- Data as of 2026-08-30T08:39:29.467469+00:00.