Omnigent
by Omnigent · Open-source meta-harness for composing, governing and sharing AI agent sessions
BenchRank score
Screenshots of Omnigent
Homepage
Overview
Omnigent is an open-source layer over AI agent harnesses — Claude Code, Codex, Pi or ones you write yourself. A runner wraps each agent in a sandboxed, uniform session that restricts filesystem and network access and hides credentials; a server adds policies such as spend caps and model routing, plus shared history. Sessions are reachable from the terminal, web, apps and a REST API.
- Best for
- Teams running several AI coding harnesses who want one layer for policies, sandboxing and shared sessions.
- Pricing
- No prices are shown on the captured page; the project is released under Apache 2.0 and installed by the user.
- Runs on
- macOSSelf-hostedCLI
Strengths and trade-offs
Strengths
- One layer over Claude Code, Codex, Pi and your own agents
- OS sandbox limits filesystem and network access, hides credentials
- Sessions available from terminal, web, mobile and a REST API
- Apache 2.0; installs via curl, uv, pip or Homebrew
Trade-offs
- Described as alpha software on its own site
- Custom agents and harnesses must be defined in YAML
- No pricing, hosted option or support terms shown in the captured text
How Omnigent markets itself
A structured read of the promise, proof and page design on Omnigent’s captured homepage.
Homepage capture
“Omnigent”
- Angle: Category creation
- Hero: Product video demo
Pricing
Published plans and prices from Omnigent’s own pricing page.
How this score is made up
Each dimension is scored out of 100 and combined into the headline score using fixed weights.
MCP support
Whether an agent can drive the product through the Model Context Protocol, and how much setup that takes.
API quality
Public API surface: machine-readable spec, official SDKs, documented auth, errors, rate limits and versioning.
Documentation
Publicly reachable docs — coverage, freshness, code samples and machine readability.
Agent friendliness
How readable the site is to an automated client: llms.txt, structured data, server-rendered content, crawler access.
Changelog
A public, dated record of what shipped and when — the clearest signal that a product is still alive.
Marketing site structure
Whether the site answers a buyer's questions: clear positioning, the pages that matter, and accessibility.
Page speed
How fast the site loads for real visitors: Chrome UX Report 75th-percentile LCP, INP and CLS, with a Lighthouse mobile run standing in where a site has too little traffic for field data.
Operational trust
Status page and incident history, security disclosure, compliance and data-processing documentation.
Measured, but not part of the score
Useful to know, but not a mark for or against the product — so these do not affect the ranking.
Openness
Source availability, self-hosting, data export and open standards. Scored and shown, but not part of the composite — paid SaaS is not worse for being paid SaaS.
Maintenance
Release cadence and repository activity. Scored and shown, but not part of the composite — it is only measurable for open repositories.
This doesn’t look right — report a problem with Omnigent’s score
Where this comes from
The Omnigent pages BenchRank reads when it scores the product — its documentation, release notes, status and security pages, and its repository where there is one.
Alternatives in Code Assistants
Ranked 1
78 — BenchRank score out of 100Superset
Superset · Desktop app for running coding agents in parallel Git worktrees
Best for: Developers on macOS running several CLI coding agents in parallel across isolated Git worktrees
Ranked 2
77.9 — BenchRank score out of 100Warp
Warp · Terminal for running and orchestrating coding agents
Best for: Developers running coding agents like Claude Code or Codex who want them managed in one terminal.
Ranked 3
74.2 — BenchRank score out of 100Frontman
Frontman · AI website editor for existing WordPress, Next.js, Astro and Vite sites
Best for: Designers, PMs and marketing teams editing existing sites without waiting on developer tickets.
Is this your product?
Claim Omnigent to manage its profile. Claiming lets you suggest edits to the descriptive fields — it never changes scores or rankings.