majiayu000Community·11 Agent Skills Included

litellm-rs

High-performance Rust gateway routing across 100+ model providers

Routes requests across 100+ model providers through one OpenAI-compatible API with load balancing, failover, and cost tracking. Eliminates vendor lock-in, manual retry logic, and scattered provider SDKs in production deployments. Guides coding agents through provider integration, routing, caching, auth, streaming, and observability architecture with verified source-level references.

104|19

↗

npx skills add majiayu000/litellm-rs --all -g -y

Available:

Instructs the agent on the gateway's architecture, provider tier system, build and test commands, and contribution workflow so it can modify the Rust codebase correctly.

All Skills in This Repository (11)

Pure Emerald Level Indicators

📦 In Repo

majiayu000

a2a-protocol

Standardize agent-to-agent messaging with JSON-RPC 2.0 and a task state machine.

config-architecture

Load and validate LiteLLM-RS gateway configurations from YAML files.

error-handling

Standardize error handling for the LiteLLM-RS gateway with structured variants and HTTP status mappings.

provider-development

Document architecture and best practices for adding and migrating LiteLLM-RS providers.

observability-architecture

Configure Prometheus metrics, OpenTelemetry traces, and JSON logs for LiteLLM gateway.

routing-architecture

Implement lock-free health-aware routing across 66+ providers with seven strategies.

caching-architecture

Implement multi-tier caching with L1, L2, and L3 backends for LiteLLM-RS.

streaming-architecture

Unify provider SSE streams into OpenAI-compatible chat chunks.

auth-architecture

Authenticate and authorize API requests with JWTs, API keys, and RBAC.

mcp-gateway

Coordinate Model Context Protocol tool calls across HTTP, SSE, WebSocket, and Stdio transports.

provider-architecture

Implement the LLMProvider trait to integrate 66+ LLM providers in Rust gateways.

Community

Advanced

Frequently Asked Questions

FAQPage Schema

How to install litellm-rs?▼

Run `npx skills add majiayu000/litellm-rs --all -g -y` in your terminal to install all skills in this suite globally.

What does litellm-rs do?▼

It is a self-hosted Rust gateway that exposes one OpenAI-compatible API and intelligently routes requests across 100+ model providers with failover, caching, and rate limiting.

How do I add a new model provider?▼

OpenAI-compatible providers need only one catalog entry, while custom providers follow the Tier 2 guide covering the LLMProvider trait, error handling, and factory registration.

Does it work with Claude Code and other coding agents?▼

Yes. The skills follow the universal SKILL.md standard and give agents verified architecture guidance for routing, auth, streaming, caching, and observability.

How is litellm-rs different from Python LiteLLM?▼

It is a Rust rewrite built for production throughput and low latency, with async I/O, type-safe configuration, and a stable versioned OpenAI-compatible contract.