Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
Automated daily memory backfill for OpenClaw sessions
Scrape and analyze OpenClaw JSONL session logs to reconstruct and backfill agent memory files. Use when: (1) Memory appears incomplete after model switches, (2) Verifying memory coverage, (3) Reconstructing lost memory, (4) Automated daily memory sync via cron/heartbeat. Supports simple extraction and LLM-based narrative summaries with automatic secret sanitization.
skill openclawclawhub Free
Scrape and analyze OpenClaw JSONL session logs to reconstruct and backfill agent memory files. Use when: (1) Memory appears incomplete after model switches, (2) Verifying memory coverage, (3) Reconstructing lost memory, (4) Automated daily memory sync via cron/heartbeat. Supports simple extraction and LLM-based narrative summaries with automatic secret sanitization.
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
- memory_sync.py, SECRET_PATTERNS.md, SKILL.md
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
- 1.0.1
Provenance
- Publisher
- mpesavento
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Memory Sync
Tool for maintaining agent memory continuity across model switches with automatic secret sanitization.
Installation
Requires Python 3.11+ and click: pip install click # Optional: for direct API summarization (only if not using OpenClaw backend) pip install openai
Quick Start
# Run directly from skill directory python ~/.openclaw/skills/memory-sync/memory_sync.py compare # Or create an alias for convenience alias memory-sync="python ~/.openclaw/skills/memory-sync/memory_sync.py" # Check for gaps memory-sync compare # Backfill today's memory (simple extraction - fast, no LLM) memory-sync backfill --today # Backfill with LLM narrative (uses OpenClaw's native model - no API key needed) memory-sync backfill --today --summarize # Backfill all missing memory-sync backfill --all
Commands
CommandDescriptioncompareFind gaps between session logs and memory filesbackfill --todayGenerate memory for current daybackfill --since YYYY-MM-DDBackfill from date to presentbackfill --allBackfill all missing datesbackfill --incrementalBackfill only changed dates since last runextractExtract conversations matching criteriasummarize --date YYYY-MM-DDGenerate LLM summary for a single daytransitionsList model transitionsvalidateCheck memory files for consistency issuesstatsShow coverage statistics
Simple Extraction vs LLM Summarization
The backfill command supports two modes: Simple Extraction (default, without --summarize): Fast, no LLM or API calls needed Extracts topics via keyword frequency analysis Identifies key user questions and assistant responses Detects decision markers from text patterns Produces structured output with Topics, Key Exchanges, Decisions sections With --preserve: Hand-written content is appended to the end of the new file Best for: Quick backfills, initial setup, systems without LLM access LLM Summarization (with --summarize) - Recommended: Uses LLM to generate narrative summaries Produces coherent 2-4 paragraph prose Better context and insight extraction With --preserve: Existing content is passed to the LLM with instructions to incorporate it into the new summary, maintaining temporal order and thematic structure Best for: Daily automation, high-quality memory files Recommended for regular use: # Best quality: LLM summary that incorporates any existing notes memory-sync backfill --today --summarize --preserve Both modes automatically sanitize secrets before writing.
Initial Setup
# Check what's missing memory-sync compare # Backfill everything (may take time) memory-sync backfill --all
Nightly Automation (Recommended)
# Best: LLM summary that incorporates any existing notes memory-sync backfill --today --summarize --preserve # Smart: Process only days changed since last run memory-sync backfill --incremental --summarize --preserve # Or use a specific backend if preferred memory-sync backfill --today --summarize --preserve --summarize-backend anthropic
Catch-Up After Gaps
# Backfill from last week to present memory-sync backfill --since 2026-01-28 --summarize
Regenerate with Preserved Content
# Keep hand-written notes when regenerating memory-sync backfill --date 2026-02-05 --force --preserve --summarize
Secret Sanitization
All content is automatically sanitized to prevent secret leakage: 30+ explicit patterns: OpenAI, Anthropic, GitHub, AWS, Stripe, Discord, Slack, Notion, Google, Brave, Tavily, SerpAPI, etc. Structural detection: JWT tokens, SSH keys, database connection strings, high-entropy base64 Generic patterns: API keys, tokens, passwords, environment variables Defense-in-depth: Secrets redacted at every stage (extraction, LLM processing, file writes, CLI display) Secrets are replaced with [REDACTED-TYPE] placeholders. See SECRET_PATTERNS.md for complete pattern list.
Summarization Backends
The --summarize flag supports multiple backends via --summarize-backend: BackendDescriptionAPI Key Requiredopenclaw (default)Uses OpenClaw's sessions spawn with your configured modelNoanthropicDirect Anthropic API via openai packageANTHROPIC_API_KEYopenaiDirect OpenAI API via openai packageOPENAI_API_KEY
Examples
# Default: use OpenClaw's native model (no API key needed) memory-sync backfill --today --summarize # Explicit backend selection memory-sync backfill --today --summarize --summarize-backend openclaw memory-sync backfill --today --summarize --summarize-backend anthropic memory-sync backfill --today --summarize --summarize-backend openai # Override model for any backend memory-sync backfill --today --summarize --model claude-sonnet-4-20250514 memory-sync backfill --today --summarize --summarize-backend openai --model gpt-4o The openclaw backend is recommended as it: Uses your existing OpenClaw configuration Requires no separate API keys Leverages whatever model you have configured in OpenClaw
Nightly Cron (3am)
Process today with LLM summary, preserving any existing notes: 0 3 * * * cd ~/.openclaw/skills/memory-sync && python memory_sync.py backfill --today --summarize --preserve >> ~/.memory-sync/cron.log 2>&1
Smart Incremental Mode
Automatically detects changes since last run: # Initial backfill (run once, simple extraction for speed) python memory_sync.py backfill --all # Then set up nightly incremental with LLM summaries 0 3 * * * cd ~/.openclaw/skills/memory-sync && python memory_sync.py backfill --incremental --summarize --preserve >> ~/.memory-sync/cron.log 2>&1 State is tracked in ~/.memory-sync/state.json.
Configuration
Default paths: Session logs: ~/.openclaw/agents/main/sessions/*.jsonl Memory files: ~/.openclaw/workspace/memory/ Override with CLI flags: --sessions-dir /path/to/sessions --memory-dir /path/to/memory Environment variables (only for direct API backends): ANTHROPIC_API_KEY - Required for --summarize-backend anthropic OPENAI_API_KEY - Required for --summarize-backend openai The default openclaw backend requires no API keys - it uses your OpenClaw configuration. # Only needed if using direct API backends export ANTHROPIC_API_KEY=sk-ant-... export OPENAI_API_KEY=sk-...
Content Preservation
The --preserve flag behavior depends on whether --summarize is used: Without --summarize (simple extraction): Hand-written content (after footer marker) is appended verbatim to the end of the newly generated file The new extraction replaces the auto-generated portion, your notes are kept at the end With --summarize (LLM mode): Existing hand-written content is passed to the LLM as context The LLM is instructed to incorporate your notes into the new summary Result: Your insights are woven into a coherent narrative, not just appended Example: # Regenerate with LLM, incorporating existing notes into the summary memory-sync backfill --date 2026-02-05 --force --preserve --summarize Auto-generated markers: Header: *Auto-generated from N session messages* Footer: *Review and edit this draft to capture what's actually important.* Content after the footer marker is considered hand-written and will be preserved.
Backfill Options
Date selection (choose one): --date YYYY-MM-DD - Single specific date --today - Current date only (for nightly automation) --since YYYY-MM-DD - From date to present (for catch-up) --all - All missing dates (for initial setup) --incremental - Only dates changed since last run (smart automation) Additional flags: --dry-run - Show what would be created without creating files --force - Overwrite existing files (required for regeneration) --preserve - Keep hand-written content when regenerating --summarize - Use LLM for narrative summaries --summarize-backend BACKEND - Backend for summarization: openclaw (default), anthropic, openai --model MODEL - Model override for summarization (default varies by backend)
Performance
ModeTime per DayBest For--all5-10 min Γ N daysInitial setup only--since5-10 min Γ N daysRecovery after gaps--today30-60 secNightly automation--incremental30-60 sec Γ changed daysSmart automation
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
2 Docs1 Scripts
- SKILL.md
- SECRET_PATTERNS.md
- memory_sync.py