What is OpenClaw memory-wiki?

Memory-wiki is a bundled plugin that compiles durable memory into a navigable knowledge vault with structured claims, evidence, contradiction detection, freshness tracking, and compiled digests.

What is new in OpenClaw v2026.4.7?

Key features include memory-wiki GA, first-class CLI inference hub, webhook ingress for TaskFlows, Gemma 4 and Arcee AI support, Ollama vision detection, and SSRF security hardening.

How do OpenClaw webhook TaskFlows work?

A bundled webhook ingress plugin lets external apps trigger and drive bound TaskFlows through per-route shared-secret endpoints, enabling native integrations without custom code.

What is the OpenClaw inference hub?

The openclaw infer command provides provider-backed inference across model, media, web, and embedding tasks with auto-fallback across auth-backed providers.

Is OpenClaw memory-wiki production ready?

Yes, memory-wiki shipped as a GA bundled plugin in v2026.4.7 with full support for structured claims, compiled digests, and freshness-weighted search.

← Back to dashboard

clawsmith.com/signal/openclaw-v2026-4-7-memory-wiki-inference-webhook

🔥 HypeUnknownOpenClaw CoreLive

OpenClaw v2026.4.7 Ships Memory-Wiki, Inference Hub, and Webhook TaskFlows

Major release restores bundled memory-wiki with structured claims/evidence and compiled digests. Adds first-class CLI inference hub across models, media, web, and embeddings. New webhook ingress plugin enables external automation to drive TaskFlows via shared-secret endpoints. Also includes Gemma 4 support, Arcee AI provider, and SSRF hardening.

Product Idea from this Signal

A memory system that gives OpenClaw agents persistent recall that survives session crashes and context window degradation

49.8k ▲

OpenClaw agents lose their entire conversation history between sessions even when the files exist on disk. Silent daily session resets wipe agent memory without warning. Meanwhile, every frontier LLM degrades past 50K tokens (proven by Chroma across 18 models), meaning even within a session, agents progressively forget earlier context. ByteDance's OpenViking (19K stars in two weeks) proves massive demand for agent memory infrastructure. This tool gives OpenClaw agents a persistent, queryable memory layer that survives crashes, session boundaries, and context window limits by storing structured knowledge externally and injecting only relevant memories per turn.

DEVTOOLCLIAI-AGENTOPEN-SOURCE

CompetitiveView Opportunity →