Delete page "Home"

Home.md

@@ -1,32 +0,0 @@
-# go-ratelimit Wiki
-
-Token counting, model quotas, and sliding window rate limiter. Module: `forge.lthn.ai/core/go-ratelimit`
-
-## Architecture
-
-Provides rate limiting primitives for AI model API calls. Tracks token usage per model, enforces quotas, and implements sliding window algorithms.
-
-### Features
-
-- **Token counting**: Estimate token usage before API calls
-- **Model quotas**: Per-model rate limits with configurable windows
-- **Sliding window**: Smooth rate limiting without burst spikes
-- **YAML config**: Load quota definitions from configuration files
-
-### Usage
-
-```go
-limiter := ratelimit.New(ratelimit.Config{
-    Models: map[string]ratelimit.ModelQuota{
-        "claude-opus-4": {TokensPerMinute: 100000, RequestsPerMinute: 60},
-    },
-})
-
-if limiter.Allow("claude-opus-4", estimatedTokens) {
-    // proceed with API call
-}
-```
-
-## Dependencies
-
-- `gopkg.in/yaml.v3` — Configuration parsing