axonhub

⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.

24 articles 2.2k View on GitHub ↗
24 articles
How to Optimize LLM Request Timeout and Performance Tuning in AxonHub

Optimize LLM request timeout and performance tuning in AxonHub by configuring hierarchical timeouts in conf.go. Set HTTP, orchestration, and provider-specific limits for improved workload latency.

performance
Mar 6, 2026
How to Scale AxonHub Horizontally with Kubernetes Helm Charts

Scale AxonHub horizontally using Kubernetes Helm charts and the looplj/axonhub repository. Configure replica counts or enable autoscaling for efficient resource management.

how-to-guide
Mar 6, 2026
How to Debug Request Failures Using Trace and Request Logs in AxonHub

Debug request failures in AxonHub with AH Trace and Request IDs. Learn how to use these headers and logs for efficient end-to-end troubleshooting in your repository.

how-to-guide
Mar 6, 2026
How to Manage API Key Rotation and Disabled Key Recovery in AxonHub

Learn to manage AxonHub API key rotation and disabled key recovery. Securely rotate keys, switch channels, disable old ones, and recover accidentally disabled keys with ease.

how-to-guide
Mar 6, 2026
How to Configure Cache Settings with Redis for Production Deployments in AxonHub

Learn to configure Redis cache settings for AxonHub production deployments. Set environment variables and initialize your store for optimal performance. Explore the Redis cache setup.

how-to-guide
Mar 6, 2026
How to Implement Custom LLM Transformers for Provider Compatibility in AxonHub

Learn to implement custom LLM transformers in AxonHub. Create structs with TransformRequest and TransformResponse methods for seamless provider compatibility. Get started today!

how-to-guide
Mar 6, 2026
How to Handle Provider Quota Limits with Automatic Fallback in AxonHub

Learn how AxonHub automatically handles provider quota limits by failing over to alternative endpoints. Isolates quota pools per model for seamless operation.

how-to-guide
Mar 6, 2026
How to Migrate Existing Applications to Use AxonHub Without Code Changes

Migrate existing AI apps to AxonHub with zero code changes. Update your SDK base URL and API key thanks to OpenAI-compatible REST endpoints. Get started today.

migration-guide
Mar 6, 2026
How Channel Health Probing and Auto-Disable Work in AxonHub

Learn how AxonHub uses channel health probing and auto disable to protect LLM providers. Discover circuit breaker style testing and permanent removal of failing channels or API keys.

internals
Mar 6, 2026
How to Use the AxonHub GraphQL API for Management Operations

Manage channels, API keys, users, and more with the AxonHub GraphQL API. Discover type-safe, RBAC-protected operations implemented via gqlgen in this guide.

how-to-guide
Mar 6, 2026
How to Configure CORS Settings for Cross-Origin Requests in AxonHub

Learn how to configure CORS settings for cross-origin requests in AxonHub. Easily enable and validate CORS with simple server configuration for seamless API integration.

how-to-guide
Mar 6, 2026
How the Model Circuit Breaker Prevents Cascading Failures in AxonHub

Learn how the model circuit breaker in AxonHub stops cascading failures. It isolates failing LLM providers by adjusting load balancing to prevent error propagation.

internals
Mar 6, 2026

Have a question about this repo?

These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:

Share the following with your agent to get started:
curl -s "https://instagit.com/install.md"
Works with
Claude Codex Cursor VS Code OpenClaw Any MCP Client

Maintain an open-source project? Get it listed too →