No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by fajarhide · MCP Server · ★ 371
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is omni safe to install? View the security audit →
Less noise. More signal. Cut your AI token consumption by up to 90%. OMNI is a smart terminal layer that intelligently filters and prioritizes command output before it reaches your AI agent. By preventing your AI from getting confused by noisy output, you get accurate answers faster while saving massive amounts of token costs. Fully transparent. You're always in control. The Problem: Expensive Tokens & Noisy Outputs When you use autonomous AI agents (like Claude Code) in your terminal, they read everything. A simple , , or command can easily dump 10,000 to 25,000 tokens of useless terminal noise into your AI's context. This causes
| Stars | 371 |
| Forks | 34 |
| Language | Rust |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 66.5219920813333/100 |
| Open Issues | 24 |
| Last Updated | 2026-09-23 |
| Created | 2026-03-15 |
| Platforms | claude-code, cli, mcp, rust |
| Est. Tokens | ~24k |
Looking for a omni alternative? If you're comparing omni with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The context intelligence layer for AI coding agents. Compressing noise, routing content to the right strategy,
The control plane for AI coding agents.
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, an
Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted
Config-driven CLI tool that compresses command output before it reaches an LLM context
Universal CLI for Agent Skills. Access 40,000+ skills from SkillsMP and sync them to Cursor, Claude Code, GitH
Explore other popular mcp server tools:
omni is Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.. It is categorized as a MCP Server with 371 GitHub stars.
omni is primarily written in Rust. It covers topics such as agentic-ai, ai-agents, antigravity.
You can find installation instructions and usage details in the omni GitHub repository at github.com/fajarhide/omni. The project has 371 stars and 34 forks, indicating an active community.
omni is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to omni on Agent Skills Hub include homebrew-pandafilter, ai-devkit, entroly. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: