Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· Productivity
Honcho Memory Multiplexer
Install and enable Honcho + the @alloralabs/honcho-memory-mux extension, migrate legacy file memory, and update workspace instructions so agents use memory v...
skill openclawclawhub Free
Install and enable Honcho + the @alloralabs/honcho-memory-mux extension, migrate legacy file memory, and update workspace instructions so agents use memory v...
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, extension/README.md, extension/dist/index.d.ts, extension/dist/index.js, extension/index.ts, extension/openclaw.plugin.json
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 0.1.0
Provenance
- Publisher
- spooktheducks
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Honcho + Memory Mux Setup
This skill installs and enables: @honcho-ai/openclaw-honcho (Honcho tools + integration) @alloralabs/honcho-memory-mux (multiplexed memory behavior) Then it migrates legacy memory files, updates agent docs, and validates runtime behavior.
What βmemory muxβ means in practice
After setup, memory behavior should be: Primary retrieval: Honcho tools (honcho_context, honcho_search, etc.) Secondary retrieval: local memory files (MEMORY.md, memory/*.md) via memory_search / memory_get Durability: pre-compaction flush writes significant session learnings to memory/YYYY-MM-DD.md Fallback safety: if Honcho is unavailable, file-based memory still works This is intentionally complementary, not a hard cutover.
Step 0: Preflight and safety checks
Before doing anything destructive: Resolve workspace root from: WORKSPACE_ROOT ~/.openclaw/openclaw.json (agent.workspace or agents.defaults.workspace) ~/.openclaw/workspace Confirm directory exists Inform user this process can upload memory files to Honcho
Step 1: Install + enable Honcho plugin
Use OpenClaw plugin manager (not workspace npm install): openclaw plugins install @honcho-ai/openclaw-honcho openclaw plugins enable openclaw-honcho If gateway logs show missing SDK deps: cd ~/.openclaw/extensions/openclaw-honcho npm install Restart gateway if required.
Step 2: Install + enable memory mux extension
Install and enable the memory-mux extension: openclaw plugins install @alloralabs/honcho-memory-mux openclaw plugins enable @alloralabs/honcho-memory-mux If the extension is local/unpublished, install from path or git URL per your release flow. After enabling: Verify plugin appears in openclaw plugins list Verify gateway boots cleanly (no extension load errors) Verify both Honcho tools and memory_search / memory_get are present at runtime
Step 3: Verify Honcho connectivity (self-hosted)
Set HONCHO_BASE_URL (example: http://localhost:8000) HONCHO_API_KEY may be optional depending on auth config If user needs local Honcho quickly: git clone https://github.com/plastic-labs/honcho cd honcho cp .env.template .env cp docker-compose.yml.example docker-compose.yml docker compose up -d Do not migrate until connection is verified.
Step 4: Detect and classify legacy memory files
Scan workspace for:
User/owner memory inputs
USER.md IDENTITY.md MEMORY.md memory/** (recursive) canvas/** (recursive)
Agent/self memory inputs
SOUL.md AGENTS.md (and AGENT.md if present in this workspace) TOOLS.md BOOTSTRAP.md HEARTBEAT.md Present a clear preview before upload: count files per class total bytes per class any unreadable/skipped files Ask for explicit confirmation.
Step 5: Upload to Honcho using peer-separated sessions
Create/ensure: workspace (HONCHO_WORKSPACE_ID or openclaw) peer owner peer openclaw migration session (e.g. migration-upload-<timestamp>) Add both peers to session, then upload files: user/owner files β owner agent/self files β openclaw If any upload fails: stop report exact file and error keep local files unchanged Report summary: uploaded user file count uploaded agent file count failed/skipped files
Step 6: Update workspace docs (including AGENT.md compatibility)
Update/create memory instructions in: AGENTS.md SOUL.md BOOTSTRAP.md AGENT.md (if this workspace uses it) Preserve custom content; only replace memory-specific sections.
Required policy text to add
Memory retrieval order First try honcho_context / honcho_search / honcho_recall If needed, use memory_search + memory_get for local file recall Use honcho_session for same-session recall Memory write behavior Important durable facts can be written via honcho_write Pre-compaction flush writes concise durable notes to memory/YYYY-MM-DD.md Failure handling If Honcho unavailable: continue with local memory tools, state degraded mode Never claim memory certainty without retrieval evidence Transparency When memory influences an answer, be able to explain source class (Honcho recall vs local file recall vs current-session context)
Step 7: Add/refresh practical memory operating conventions
Ensure docs reflect these conventions the agent has been using: Do not preload everything into active reasoning if not needed Prefer targeted retrieval over huge static context injection Treat disagreement as signal: preserve conflicting observations; do not silently average Use pre-compaction flushes to avoid losing high-value context during long sessions Separate memory types conceptually: durable facts episodic notes scratch/working notes Even if physical storage is mixed, behavior should preserve this distinction.
Step 8: Optional (recommended) no-fork observability add-on
Without modifying OpenClaw gateway source, the memory-mux extension can emit: a small memory load manifest per session start (what memory sources were pulled) a pre-compaction write report (what was persisted) Store under: memory/manifests/YYYY-MM-DD/<session>.json This makes memory behavior debuggable while keeping upstream updates painless.
Step 9: Validate end-to-end behavior
Run a quick live test: Ask agent about a known historical fact only in migrated memory Confirm retrieval path works (Honcho first, fallback available) Trigger/perform pre-compaction flush Confirm new note appears in memory/YYYY-MM-DD.md Re-ask fact in a new turn/session to validate durability
Wrap-up report to user
Provide: installed/enabled plugin list Honcho connectivity mode (managed vs self-hosted) files discovered, uploaded, skipped docs updated (AGENTS.md, SOUL.md, BOOTSTRAP.md, AGENT.md if present) any follow-up actions Reference docs: https://docs.honcho.dev https://github.com/plastic-labs/honcho
Guardrails
Never delete user memory files automatically unless user explicitly asks Never proceed with migration on failed Honcho connectivity Never silently ignore upload errors Prefer reversible edits and clear summaries
Category context
Workflow acceleration for inboxes, docs, calendars, planning, and execution loops.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
3 Scripts2 Docs1 Config
- SKILL.md
- extension/README.md
- extension/dist/index.d.ts
- extension/dist/index.js
- extension/index.ts
- extension/openclaw.plugin.json