awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
decolua avatar

decolua/9router

0
View on GitHub↗

9router

9router is an AI model gateway designed to route requests from AI coding tools to multiple model providers through a single unified API. It provides administration for self-hosted AI proxy deployments, allowing users to manage API keys and model access on local servers or edge networks.

The system differentiates itself through multi-provider API normalization, which translates incompatible request and response formats to ensure compatibility across different AI models. It features AI provider failover management to automatically switch between providers or accounts when quotas are exhausted or errors occur, and implements multi-account rotation to bypass individual provider limits.

The gateway covers a broad set of capabilities including token optimization via payload compression, spending analysis and quota tracking, and encrypted configuration synchronization across devices. Traffic management is handled through capability-based routing and outbound proxy support, while security is maintained via API access keys and automated token refreshment.

The application supports containerized deployment and can be hosted on local machines, virtual servers, or global edge networks.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI
9router.com
↗

Features

  • AI Gateways - Acts as a unified AI gateway that routes requests from coding tools to multiple model providers via a single API.
  • Model Proxy Gateways - Acts as a unified interface gateway that proxies requests from coding tools to multiple LLM providers.
  • Failover Strategies - Distributes requests across model pools using fallback, round-robin, or capacity-based selection strategies.
  • Model Format Translators - Translates request and response schemas between different LLM provider APIs to ensure cross-tool compatibility.
  • Fallback Configurations - Provides ordered backup model lists to ensure continuity when a primary model fails or hits its quota.
  • Model Provider Management - Centralizes the management of multiple AI model provider API keys and regional clusters.
  • Failover Mechanisms - Automatically switches between AI model providers or accounts when quotas are exhausted or errors occur.
  • Provider Compatibility - Normalizes incompatible request and response formats between different AI providers to ensure tool compatibility.
  • Self-Hosted AI Infrastructure - Enables deployment of a private AI proxy gateway on local servers or edge networks for managing API keys.
  • API Access Security - Secures the gateway by validating incoming requests using API keys or secrets.
  • Endpoint Translation Maps - Implements logic to translate external API endpoint formats into standardized internal routing paths for provider compatibility.
  • Capability-Based Routing - Directs requests to specific model providers based on the required task, such as image generation or web searching.
  • AI Agent Skills - Provides a mechanism for defining and sharing reusable skill sets that AI agents can fetch to perform complex tasks.
  • Model Request Routing - Directs embedding requests to specific AI backends by managing request bodies and header configurations.
  • Gateway Management - Provides a web-based administrative interface for configuring proxy settings, quotas, and provider connections.
  • Response Synthesis Pipelines - Sends prompts to multiple models in parallel and utilizes a judge model to synthesize a final coherent response.
  • Capability-Based Routing - Ensures specialized inputs are sent to the most capable providers by reordering target models per request.
  • Model Response Synthesis - Sends a single prompt to multiple AI models simultaneously and uses a judge model to merge the results.
  • Provider Account Rotation - Distributes outgoing API calls across a pool of multiple accounts to bypass individual provider quota restrictions.
  • Sampling Provider Fallbacks - Automatically reroutes traffic to secondary model providers when primary services hit rate limits or return errors.
  • Token Optimizers - Optimizes token usage by tracking limits and automatically switching to more cost-effective AI models.
  • Token Optimization Utilities - Reduces LLM token consumption and operational costs through payload compression and usage tracking.
  • Tool Output Compression - Compresses verbose tool outputs like logs and diffs to minimize token consumption in AI requests.
  • AI Usage Analytics - Tracks token usage and analyzes spending trends across different models to generate expenditure reports.
  • Token-Aware Log Compression - Compresses verbose tool outputs and logs to reduce token consumption before sending requests to models.
  • Account Rotation Strategies - Bypasses individual provider quota limits by rotating requests across a pool of multiple accounts.
  • Traffic Routing Proxies - Forwards outbound traffic through HTTP or SOCKS proxies to bypass network restrictions.
  • Edge Proxies - Implements edge-based proxying to manage traffic distribution and bypass network restrictions.
  • Token Consumption Trackers - Monitors real-time token consumption and provides reset countdowns and cost estimates for service tiers.
  • AI Tools - Router for accessing multiple AI coding models.
17,690 stars·2,738 forks·JavaScript·MIT·41 views

Star history

Star history chart for decolua/9routerStar history chart for decolua/9router

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Projects sharing features with 9router

These projects share indexed features with 9router. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • chopratejas/headroomchopratejas avatar

    chopratejas/headroom

    79,078View on GitHub↗

    Headroom is an AI gateway proxy and token optimizer designed to reduce the cost and latency of large language model interactions. It functions as an intermediary that intercepts traffic between clients and providers to apply context compression, request routing, and format translation. The system differentiates itself through a Model Context Protocol server implementation that delivers compression and retrieval tools to compatible AI hosts. It employs a content-aware compression pipeline and tiered importance scoring to trim redundant data from logs and tool outputs while preserving essential

    Pythonagentaianthropic
    View on GitHub↗79,078
  • alibaba/higressalibaba avatar

    alibaba/higress

    7,558View on GitHub↗

    Higress is an AI API gateway and cloud-native traffic manager that functions as a Kubernetes ingress controller. It provides a centralized system for routing, securing, and optimizing traffic directed toward large language models, AI agents, and microservice architectures. The project distinguishes itself through deep AI orchestration, including the ability to host and manage Model Context Protocol servers that transform REST APIs into tools for AI agents. It features specialized AI infrastructure for model request proxying, protocol translation across multiple providers, and semantic-based c

    Goai-gatewayai-nativeapi-gateway
    View on GitHub↗7,558
  • cloudflare/moltworkercloudflare avatar

    cloudflare/moltworker

    9,909View on GitHub↗

    Moltworker is an AI agent sandbox and model orchestrator designed for the secure execution of untrusted code and shell commands generated by large language models. It functions as a gateway proxy that routes requests to multiple AI providers through a unified interface, integrating a container runtime backed by S3-compatible object storage to persist state across ephemeral lifecycles. The system distinguishes itself by combining an AI model orchestrator with a headless browser controller for automated web scraping and screenshot capture. It manages the full lifecycle of AI agents, including m

    TypeScriptai-agentscloudflare-workers
    View on GitHub↗9,909
  • vercel/vercelvercel avatar

    vercel/vercel

    16,550View on GitHub↗

    Vercel is a cloud platform for building, deploying, and scaling web applications. It provides a unified infrastructure that automates the build process by detecting project frameworks and distributing static and dynamic content through a global content delivery network. The platform executes application logic using serverless functions that scale automatically based on real-time traffic demand. The platform distinguishes itself through a centralized AI gateway that proxies requests to multiple model providers, enabling standardized authentication, observability, and cost tracking. It supports

    TypeScriptclicloudcommand
    View on GitHub↗16,550
Compare all 30 related projects→

Frequently asked questions

What does decolua/9router do?

9router is an AI model gateway designed to route requests from AI coding tools to multiple model providers through a single unified API. It provides administration for self-hosted AI proxy deployments, allowing users to manage API keys and model access on local servers or edge networks.

What are the main features of decolua/9router?

The main features of decolua/9router are: AI Gateways, Model Proxy Gateways, Failover Strategies, Model Format Translators, Fallback Configurations, Model Provider Management, Failover Mechanisms, Provider Compatibility.

Which projects share features with decolua/9router?

Projects with overlapping indexed features include: chopratejas/headroom — Headroom is an AI gateway proxy and token optimizer designed to reduce the cost and latency of large language model… alibaba/higress — Higress is an AI API gateway and cloud-native traffic manager that functions as a Kubernetes ingress controller. It… cloudflare/moltworker — Moltworker is an AI agent sandbox and model orchestrator designed for the secure execution of untrusted code and shell… vercel/vercel — Vercel is a cloud platform for building, deploying, and scaling web applications. It provides a unified infrastructure… boundaryml/baml — BAML is a prompt engineering framework and LLM client generator that defines AI prompts as type-safe functions. It… quantumnous/new-api — This project is an AI model API gateway and proxy server designed to provide a unified interface for interacting with…