Operate and troubleshoot the LiteLLM proxy and Python SDK, including provider routing, authentication, budgets, reliability, caching, guardrails, observability, deployment, and public-hosting security.
Operate, configure, secure, and troubleshoot the LiteLLM AI gateway (proxy) and Python SDK: run the proxy (litellm --config), route to 100+ providers through one OpenAI-compatible API, configure model lists and routing/reliability, virtual keys, teams, budgets, rate limits, caching, guardrails, observability, and spend, and diagnose request failures. Use when deploying or running a LiteLLM proxy or gateway (config.yaml, ghcr.io/berriai/litellm), wiring the Python SDK or OpenAI SDK through it, or hardening a public-facing deployment. Do not use for operating a single inference engine (vllm, llama-cpp), for engine-selection methodology (ml-engineering), or for building applications on top of an LLM API (backend/frontend engineering).
evals/evals.json
JSON
Other
README.md
Markdown
Other
templates/proxy-config-record.md
Markdown
Other
templates/proxy-deployment.md
Markdown
Other
tests/test_litellm_health.py
Python
Reference
references/00-source-index.md
Markdown
Reference
references/01-quickstart-and-sdk.md
Markdown
Reference
references/02-config-and-routing.md
Markdown
Reference
references/03-keys-teams-budgets-spend.md
Markdown
Reference
references/04-caching-and-guardrails.md
Markdown
Reference
references/05-observability-and-logging.md
Markdown
Reference
references/06-deployment.md
Markdown
Reference
references/07-security-and-public-hosting.md
Markdown
Reference
references/08-troubleshooting.md
Markdown
Script
scripts/litellm-health
SKILL.md
SKILL.md
Markdown
Guides safe administration and troubleshooting of remote Linux, BSD, and macOS hosts using SSH, Ansible, or Paramiko, with platform discovery, controlled changes, rollback plannin…
Enables agents to design and operate software release processes, CD pipelines, progressive delivery, versioning, quality gates, rollback plans, compliance evidence, and DORA metri…
Helps agents design and improve reliable production systems using SLOs, observability, error budgets, incident command, on-call practices, postmortems, and operational templates.
Helps agents inspect and operate PostgreSQL safely, including configuration, query plans, vacuum, WAL/PITR, replication, failover, extensions, upgrades, and read-only diagnostics.
Deploy, configure, and troubleshoot Traefik v3 reverse proxy installations, including providers, routing, TLS/ACME, middleware, Kubernetes, observability, and production patterns.
Transforms incident, near-miss, and exercise evidence into owned follow-up work across product, engineering, testing, operations, and governance, with explicit uncertainty and ver…
Guides agents in designing, exercising, and documenting system resilience, graceful degradation, disaster recovery, restore testing, failover drills, RTO/RPO decisions, data integ…
Enables agents to operate, configure, provision, secure, troubleshoot, and integrate Grafana OSS, Enterprise, and Cloud resources through documented workflows and APIs.