by fajarhide · MCP Server · ★ 164
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
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 | 164 |
| Forks | 18 |
| Language | Rust |
| Category | MCP Server |
| License | MIT |
| Quality Score | 54.328/100 |
| Open Issues | 1 |
| Last Updated | 2026-05-05 |
| Created | 2026-03-15 |
| Platforms | claude-code, cli, mcp, rust |
| Est. Tokens | ~418k |
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.
Config-driven CLI tool that compresses command output before it reaches an LLM context
One-stop shop for AI skills and agents. Search 110K+ community skills, install and track them declaratively, a
The open-source intelligence layer for AI native development
The context intelligence layer for AI coding agents. Compressing noise, routing content to the right strategy,
One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto
Introduces a comprehensive agent-based framework for guided software development (GSD)
Explore other popular mcp server tools:
omni is A smart context filter that removes noise, refines and enhances responses, also slashes token usage by up to 90%.. It is categorized as a MCP Server with 164 GitHub stars.
omni is primarily written in Rust. It covers topics such as ai-agents, antigravity, claude-code.
You can find installation instructions and usage details in the omni GitHub repository at github.com/fajarhide/omni. The project has 164 stars and 18 forks, indicating an active community.
omni is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to omni on Agent Skills Hub include tokf, skillfile, bitloops. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.