diegosouzapw/OmniRoute

Never stop coding. Free MIT AI gateway: one endpoint, 340 providers (90+ free), 1200+ models — Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with...

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 22 minutes ago
Added to GitGenius on July 2nd, 2026
Created on February 13th, 2026
Open Issues & Pull Requests: 378 (+5)
Number of forks: 6,882
Total Stargazers: 50,530 (+20)
Total Subscribers: 294 (+1)

Repository Insights (GitGenius)

Median issue/PR response: 7.8 hours
Mean response time: 29.9 hours
90th percentile: 2.8 days
Tracked items: 3,421

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 85% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Almost all tracked open issues have seen activity in the last three months. Only 9% of issues opened in the past year have been closed. Three people close 94% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 293
New in 7 days: 192
Closed in 7 days: 188
Avg open age: 7 days
Stale 30+ days: 2
Stale 90+ days: 0

Recent activity

Opened in 7 days: 160
Closed in 7 days: 186
Comments in 7 days: 192
Events in 7 days: 945

Top labels

  • bug (1,870)
  • kilo-triaged (977)
  • enhancement (789)
  • kilo-duplicate (599)
  • providers (549)
  • backend (407)
  • kilo-auto-fix (294)
  • needs-info (274)

Detailed Description

OmniRoute is a free AI gateway that consolidates access to 237 AI providers through a single endpoint, enabling developers to connect coding tools like Claude Code, Cursor, Cline, and Copilot to multiple AI models without managing separate integrations. Written in TypeScript, the project aggregates documented free tiers across 40+ provider pools and 500+ models, offering approximately 1.6 billion free tokens per month, with potential for up to 2.1 billion tokens in the first month when accounting for signup credits.

The core value proposition centers on three primary capabilities. First, OmniRoute implements intelligent auto-fallback routing across 237 providers, automatically switching between services when rate limits are exceeded or providers fail, ensuring zero downtime during quota exhaustion. Second, the platform employs RTK and Caveman stacked compression techniques that reduce token consumption by 15 to 95 percent on eligible requests, with an average savings of approximately 89 percent on tool-heavy sessions. Third, it provides free access through 90+ providers with free tiers, including 11 permanently free providers with no token caps, requiring no credit card to begin.

OmniRoute addresses practical pain points in AI development workflows. It eliminates the need to manage multiple dashboards and API keys across different providers, maximizes utilization of monthly subscription quotas before reset, and provides cost-optimized routing that automatically selects the cheapest viable model for each request. The platform supports 24+ coding agents through unified configuration and implements production-grade infrastructure including circuit breakers, TLS stealth for geographically restricted regions, Model Context Protocol integration with 95 tools, and agent-to-agent communication capabilities.

The project's architecture includes a combo system that chains models together automatically, allowing the gateway to transition between providers seamlessly when quotas deplete or costs spike. This functionality operates with zero configuration when users select the auto model variant, with OmniRoute building virtual combos from connected providers scored in real time. The platform runs as a desktop application, progressive web application, or local service, maintaining a private, local-first approach to data handling.

Documentation is available in 42+ languages, and the project maintains active community channels including Discord, Telegram, and WhatsApp groups for support and roadmap discussion.