#rate-limiting

🦀 Ultra-minimalist, high-resilience LLM routing gateway in Rust. OpenAI-compatible with auto-retry, backoffs, circuit breakers, SIGHUP hot-reloads, and open telemetry. Ideal for free provider surfing.

Multi-tenant AI copilot for on-call engineers with grounded ticket summaries, SOP search (RAG), and RCA generation.

Monk LLM Gateway: one API in front of every model. An LLM gateway and router built from scratch (proxy, routing, retry/fallback, caching, budgets), with an interactive course.

Run Claude Code across several Claude Max accounts as if they were one: a local proxy that routes each session to the account with the most headroom and switches before a limit hits

Queue multiple Claude API requests and pace them automatically — no babysitting, no rate-limit headaches. Free, open-source, client-side only.

Multi-provider LLM gateway on FastAPI: auth, rate limiting, caching, retries, and per-model cost accounting behind one OpenAI-shaped API. Deterministic mock provider, green CI, zero secrets.

Resilient Azure OpenAI patterns: rate-limit (429) mitigation, multi-region API Management failover, graceful degradation with semantic caching, and private endpoints.

Hermes-inspired security control plane for LLM agents over private DMs: allowlist, PIN, kill switch, rate limits, injection heuristics, secret redaction, audit log.

Dated, client-side LLM cost & rate-limit (429) calculator + machine-readable pricing snapshot JSON for Anthropic & OpenAI.