Google PageRank for AI agents. 25,000+ tools indexed.

omni MCP Server

fajarhide/omni

Score: 93.6 → 0% Rank #133 MCP Server
[![AgentRank](https://agentrank-ai.com/api/v1/badge/fajarhide--omni)](https://agentrank-ai.com/tool/fajarhide--omni/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of fajarhide/omni? Claim this listing →

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.

Add AgentRank to Claude Code Discover and compare tools like fajarhide/omni — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

fajarhide/omni is a Rust tool licensed under Apache-2.0. 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. Topics: ai-agents, context-distillation, mcp, token-efficiency, antigravity, claude-code, cli, cost-reduction, homebrew, token-optimization, hooks, rust, memory, agentic-ai, context-engineering, cursor, developer-tools, llm, context-compression, prompt-caching.

Ranked #133 out of 24846 indexed tools.

In the top 1% of all indexed tools.

Has 14 contributors.

Ecosystem

Rust Apache-2.0
ai-agentscontext-distillationmcptoken-efficiencyantigravityclaude-codeclicost-reductionhomebrewtoken-optimizationhooksrustmemoryagentic-aicontext-engineeringcursordeveloper-toolsllmcontext-compressionprompt-caching

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 368

368 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 97%

376/388 issues closed → responsive maintainer

Contributors 10% 14

14 contributors → active community

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 35
Description Good
License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

Badge all embed codes →

AgentRank score for fajarhide/omni
[![AgentRank](https://agentrank-ai.com/api/v1/badge/fajarhide--omni)](https://agentrank-ai.com/tool/fajarhide--omni/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/fajarhide--omni/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/fajarhide--omni" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="fajarhide/omni"></script>

Matched Queries

topic:mcp

From the README

<div align="center">
  

<h1>OMNI</h1>
<p align="center">
    <em><b>Your agent pays twice for output it has already seen.</b> OMNI hands back a retrievable handle instead: <b>97.2%</b> off a file it reads twice. Across a whole session it takes about a tenth of the repetition your work actually contains, which was <b>1.5%</b> of file-read bytes on the corpus below. How repetitive your work is decides where you land between those two. Nothing deleted, nothing invented, and every number here replays on your own history.</em>
</p>

[🇺🇸 English](README.md) | [🇯🇵 日本語](i18n/README-ja.md) | [🇨🇳 简体中文](i18n/README-zh.md) | [🇸🇦 العربية](i18n/README-ar.md) | [🇮🇩 Bahasa Indonesia](i18n/README-id.md) | [🇻🇳 Tiếng Việt](i18n/README-vi.md) | [🇰🇷 한국어](i18n/README-ko.md)

  
  
  
  
  
  
</br></br>

```bash
brew install fajarhide/tap/omni && omni init
```

</br>

</div>

---

## What it does

**Drops the noise.** Build logs, Docker layer hashes, progress bars, ANSI colour. The
part of th
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.