Clawd-Docs v2.0 - Smart Documentation Access
Intelligent access to ClawdBot documentation with:
- Local search index - instant keyword lookup (0 tokens)
- Cached snippets - pre-fetched common answers (~300-500 tokens)
- On-demand fetch - full page when needed (~8-12k tokens)
- Freshness tracking - TTL per page type
Quick Start
Step 1: Check Golden Snippets First
Before fetching anything, check if a Golden Snippet exists:
ls ~/clawd/data/docs-snippets/Available snippets:
| Snippet | Query matches |
|---------|---------------|
| telegram-setup.md | "telegram setup" |
| telegram-allowfrom.md | "allowFrom", "access control" |
| oauth-troubleshoot.md | "token expired", "oauth error" |
| update-procedure.md | "update clawdbot" |
| restart-gateway.md | "restart", "stop/start" |
| config-basics.md | "config", "configuration" |
| config-providers.md | "add provider", "discord setup" |
| memory-search.md | "memory", "vector search", "embeddings" |
Step 2: Search Index
Check ~/clawd/data/docs-index.json for page suggestions.
Step 3: Check Full Page Cache
ls ~/clawd/data/docs-cache/ | grep "concepts_memory"
cat ~/clawd/data/docs-cache/concepts_memory.mdStep 4: Fetch Page (only if NOT in cache)
Use native web_fetch tool:
web_fetch({ url: "https://docs.clawd.bot/{path}", extractMode: "markdown" })TTL Strategy
| Page Category | TTL | Why |
|---------------|-----|-----|
| install/updating | 1 day | Always current |
| gateway/* | 7 days | Config changes |
| channels/* | 7 days | Provider updates |
| tools/* | 7 days | Features added |
| concepts/* | 14 days | Rarely changes |
| reference/* | 30 days | Stable templates |
Fallback: Full Index Refresh
web_fetch({ url: "https://docs.clawd.bot/llms.txt", extractMode: "markdown" })Data Locations
~/clawd/data/
├── docs-index.json # Search index
├── docs-stats.json # Usage tracking
├── docs-snippets/ # Cached Golden Snippets
└── docs-cache/ # Full page cache