ClawQL Learn
ClawQL Learn is the home for practical guides and, over time, structured training across the whole stack—from your first npx clawql-mcp through production deployment and optional tools.
New lesson-style modules will appear here first; deeper reference pages stay under Guides, Case studies, and Reference in the sidebar.
Start here
If you are new to ClawQL, follow this sequence:
- Quickstart — run the MCP server and connect a client in minutes
- Install — binaries, Docker, and Streamable HTTP
- MCP clients — Cursor, Claude Desktop, and other MCP hosts
- Concepts — how
searchandexecutefit together - Using search and execute —
search/executeinputs, args, fields, and pitfalls - Tools — full tool surface and behavior
- OpenClaw with ClawQL — gateway +
openclaw mcp set+ smoke path
Learn modules
Curated walkthroughs under /learn— the same links as ClawQL Learn in the sidebar.
Using search & execute
`search` / `execute` inputs, args, response fields, and common pitfalls when calling loaded OpenAPI specs.
External ingest & knowledge lake
Import Markdown or a single URL into the vault with `ingest_external_knowledge`, dry runs, and vault pairing.
Onyx enterprise search
Optional `knowledge_search_onyx`: ACL-aware semantic search over your enterprise Onyx index.
Document pipeline
Five-vendor path: Tika → Gotenberg → Stirling → Paperless → Onyx — ingest, OCR, and indexing.
Sandbox exec
Optional `sandbox_exec`: Seatbelt, Docker, or Cloudflare bridge — isolated snippets and safety notes.
Ouroboros tools
`ouroboros_*`: seed from documents, evolutionary loop, Postgres lineage, and route hints vs raw infra.
OpenClaw with ClawQL
Gateway wiring, `openclaw mcp set`, and a smoke path so agents use the same MCP surface as Cursor.
Schedule & notify workflows
`schedule` synthetics plus `notify` to Slack — threads, HITL hooks, and Label Studio handoff patterns.
Cache handoff between chats
Core `cache` tool: scratch state, TTL, namespacing, and carrying context into a new chat session.
Vault memory between chats
Durable `memory_ingest` / `memory_recall` across MCP restarts — vault paths, graph depth, and hygiene.
Audit tool & observability
Core `audit` ring buffer plus Prometheus, Grafana, and Loki — breadcrumbs without vault writes.
Related guides
Install, specs, deployment, networking, and operations pages outside /learn that pair with the modules above.
Spec configuration
OpenAPI paths, URLs, Google Discovery, merged presets, and CLAWQL_* precedence for loaded specs.
Tailscale & Headscale
Private tailnets for MCP: MagicDNS, Serve, CLAWQL_MCP_URL, ACLs, and mesh vs cluster DNS.
Kubernetes
Helm install, gRPC and HTTP, auth, rebuilds, and Kustomize patterns for dev and prod clusters.
Docker Desktop: Istio & observability
Prometheus, Grafana, Tempo, Kiali, and OTel Collector on Docker Desktop — beginner-oriented runbooks.
OpenClaw + ClawQL
Gateway product page plus cross-links to the full Learn walkthrough for `openclaw mcp set`.
Security
Golden image pipeline, Kyverno, Cosign keyless signing, Trivy/OSV gates, and supply-chain references.
Troubleshooting
Common MCP host failures, spec loading, auth, and where to look first when something breaks.
Case studies
Long-form narratives: incidents, sessions, and homelab deep dives — same cards as the home page Case studies section.
Case study: Cloudflare docs
End-to-end MCP workflow: search, execute, memory_recall, memory_ingest — deploying docs.clawql.com and fixing Worker runtime issues.
Case study: Vault + GitHub session
memory_ingest at scale, issue triage and new tracking issues, prioritization, and shipping the enterprise audit tool with full docs and Helm wiring.
Case study: Cross-thread vault recall
Before and after: repo-only search vs memory_recall — Obsidian graph, Cuckoo/hybrid memory roadmaps, wikilinks, and session resume workflows.
Case study: TrueNAS corgicave homelab
TrueNAS SCALE on a switch island: Mac errno 49, Docker/K8s utun, memory_ingest/recall, Thunderbolt vs SSH — full triage ladder and resolution.
Case study: Worker 1102 + MCP + memory
docs.clawql.com incident: Error 1102 and waitUntil warnings; search/execute on Cloudflare APIs; memory_ingest postmortem; Lighthouse CI and prevention runbook.
Case study: Slide deck vs GitHub (cache + recall)
memory_recall before filing parity issues; cache() for ephemeral scratch; 12 new issues for deck themes; memory_ingest to close the loop — April 2026 session.
Browse by stack topic
Use these hubs when you care about one slice of the product:
- Core MCP — Tools, Spec configuration, Bundled specs
- Session & automation — Session cache, Sandbox exec (
sandbox_exec), Schedule & notify workflows, Schedule synthetic checks, Slack notify, Audit tool & observability - Knowledge & documents — Document pipeline (five vendors), External ingest & knowledge lake, Onyx enterprise search (
knowledge_search_onyx), Onyx knowledge search, Flink Onyx sync - Streams & APIs — NATS JetStream, GraphQL layer
- Spec-first workflows — Ouroboros tools (
ouroboros_*), Ouroboros library - Human-in-the-loop — Schedule & notify workflows (Slack + Label Studio), HITL — Label Studio
- OpenClaw gateway — OpenClaw + ClawQL, OpenClaw with ClawQL (learn walkthrough)
Modules and certifications
Structured courses, quizzes, and badges are not published yet. When they ship, they will live under /learn (for example, dedicated paths per module) so you can bookmark https://docs.clawql.com/learn as the single entry point for training.
If you want a topic prioritized for the first module, open a discussion or issue on GitHub.
