gl0bal01

Omi — AI skill for Claude Code

AI community

Single static Go CLI for the 1min.ai REST API — parallel multi-model consensus panel, Unix-pipe composition, typed model registry.

How to install Omi

This entry records only its repository, not the path inside it, so there is no exact command to give. Open gl0bal01/omi and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Omi does

Single static Go CLI for the 1min.ai REST API — parallel multi-model consensus panel, Unix-pipe composition, typed model registry.

Alternatives in AI

Define — Definition phase - Clarify and scope problems with multi-AI consensus 2.8k ★
Claude Skill Web Clone — Methodology for faithfully cloning any website (static / React / WebGL) — without copying AI-hallucinated code 969 ★
Agentty — AI pair programming in your terminal — one static binary, sub-ms startup, any model 597 ★

README

omi

A single static Go CLI for the [1min.ai](https://app.1min.ai) REST API — with a parallel multi-model **consensus panel**, **Unix-pipe composition**, and a **typed model registry** with per-model defaults.

[![Go Version](https://img.shields.io/badge/go-1.27%2B-00ADD8?logo=go)](https://go.dev/) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) [![Status](https://img.shields.io/badge/status-v0.3.0-brightgreen.svg)](CHANGELOG.md)

omi consensus -m mini,claude,gemini-pro --synth-model best "Should we ship today?"

Why omi?

Multi-model consensus, in parallel. omi consensus fans the same prompt out to an N-model panel concurrently, then a synthesis model produces Consensus / Disagreements / Recommendation. Wall-clock = max(latency), not the sum.
Composes with the rest of your shell. TTY-aware stdin/stdout — pipe git log or Fabric patterns in, pipe streamed output through jq, tee, or another omi call out.
Typed model registry, not stringly-typed. Capability-tagged aliases (chat / code-only / vision-only) with per-model defaults that auto-apply (e.g. sonar auto-enables web search). Override via ~/.config/omi/models.json.
Stateful conversations + REPL. Named sessions persist server-side; an interactive REPL drops in when stdin is a TTY and gracefully handles Ctrl+C cancellation of in-flight streams.
Single static binary, ~6 ms cold start. No Python or Node runtime, no CGO. Production-safe defaults: Retry-After honored, resource caps, terminal-injection sanitizer.

Features

Streaming chat over Server-Sent Events for sub-second first-token latency.
Vision and document Q&A via the unified chat-with-ai endpoint with image or PDF/text/docx attachments.
Code generation with a dedicated omi code subcommand and code-capable model aliases.
Consensus mode via omi consensus, an omi client-side feature that ask