# omnigent-ai/omnigent

> Open-source meta-harness for orchestrating AI agents: unifies Claude Code, Codex, Cursor and custom agents under a common layer with policies, sandboxing and real-time collaboration from any device.

- Magnitude: 1.7 out of 10 — Steady
- Stars: 10,878 total · +15 stars measured 2026-10-18, 00:25–23:30 UTC
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-06-11 · Last push: 2026-10-18
- GitHub: https://github.com/omnigent-ai/omnigent · Homepage: https://omnigent.ai · Page: https://gitnova.dev/en/r/omnigent-ai/omnigent

## Useful for

- Run a session with multiple agents and have one review another's work
- Enforce a policy limiting an agent's tool access and session spend
- Run an agent in a Modal or E2B cloud sandbox without a local machine

## Why it’s here

- Star-counter measurements on 2026-10-18 (UTC), 00:25–23:30: 10863 → 10878 stars (+15). This is the change over that interval.
- Interest is fading: the two-day pace is 52% of the previous week and a half.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1,763
- Issues and pull requests: 10,673
- Watchers: 47
- Average over the last week: 19 per day
- Usual pace: 33 per day
- Latest release: v0.18.0 (2026-10-13)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 26, 34, 17, 41, 84, 60, 34, 33, 23, 25, 26, 21, 17, 26, 24, 20, 18, 14, 12, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-05 4.0, 10-06 3.3, 10-07 2.4, 10-08 2.5, 10-09 2.6, 10-10 2.5, 10-11 2.2, 10-12 2.1, 10-13 2.1, 10-14 2.5, 10-15 2.7, 10-16 2.6, 10-17 2.4, 10-18 2.2

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-18 23:35 UTC, updated every 30 minutes.