Request early access or book a demo
ClawQL provides the Agentic Gateway as the Foundational Platform for Auditable Production AI. Land with OpenAI-compatible inference and MCP; expand into memory, Dedicated Virtual Gateway governance, and Edge Gateways on every laptop. Self-host free on Apache 2.0, or join the managed waitlist for early access. Real estate teams: see the one-paragraph pitch to forward before your demo. Hosted evaluation targets the Developer experience (14-day window once provisioned). Gateway from $29/mo, Teams $99/mo, IDP bundle from $299/mo.
The same MCP tools — hosted for you.
Every tier below ships with core discovery and execution. Managed adds persistence, IDP, and ops.
searchRank thousands of API operations by natural-language intent. Specs stay server-side; agents get operation IDs and parameter hints. Provider catalog is empty by default — opt in with CLAWQL_PROVIDER / providers.pack / CLAWQL_TIER.
executeRun one operation with validated args over REST, GraphQL, or gRPC. Lean responses keep tool results out of your context budget.
auditIn-process ring buffer of structured events — append, list, clear. Pair with memory_ingest when you need a durable operator trail.
cacheEphemeral LRU scratch space for the active session. Use memory_* when data must survive restarts.
skills_listDiscover shipped Agent Skills (SKILL.md packs) registered on the server — including handoff and workflow recipes.
skills_getFetch a skill body by name so agents can follow vetted SOPs instead of improvising every workflow.
IDP pipeline and vault memory, hosted
Self-hosters run clawql-idp with eight co-deployed vendors. Managed accounts deliver the same compose path with upgrades, backups, and observability handled.
run_idp_pipeline
Automated Nextcloud → Docling/Tika → Gotenberg → Stirling → archive → Onyx → Coneshare — one tool call, retries and Merkle snapshots included.
memory_recall across clients
Cursor, OpenClaw, and Claude Desktop share one vault. Agents recall prior session notes without copy-paste — proven in production case studies.
knowledge_search_onyx
Hybrid enterprise search over your indexed documents. Agents ground answers in Onyx hits rather than model improvisation.
Eight vendors, one pipeline
WebDAV inbox receives uploads; processed files sync back to team folders.
Local classify + Markdown for text PDFs; route scanned/mixed pages to Docling OCR.
Layout-aware OCR for forms and W-2s; Tika handles 1,000+ text formats.
Office and HTML sources become consistent PDFs for downstream redaction.
PII redaction, split, and merge before documents enter the archive.
Nextcloud + Postgres metadata store, Onyx-indexed — the default on managed accounts. Paperless-ngx compatible for self-hosted deployments.
Hybrid search and ingestion API — agents query indexed content via knowledge_search_onyx.
VDR share links and viewer webhooks for external parties who need controlled access.
Want full control? Self-host with npm or Helm — every tool, every vendor, zero license fee.
Enterprise: dedicated node, custom fine-tuning, EU multi-region — from $3,500/mo. Contact sales to scope requirements.
Contact sales