Run any Skill in Manus with one click

memory-upgrade

Stars111

Forks21

UpdatedMay 28, 2026 at 19:27

Diagnose and fix broken memory search in OpenClaw. Enables local embeddings, hybrid search (BM25+vector), session transcript indexing, MMR diversity, and temporal decay — all running locally with zero API keys. Use when: memory_search returns empty results, agent has poor cross-session recall, user wants to upgrade their memory system, or after a fresh OpenClaw install.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

profbernardoj

profbernardoj/everclaw-community-branches

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

6 files

SKILL.md

readonly

name	memory-upgrade
description	Diagnose and fix broken memory search in OpenClaw. Enables local embeddings, hybrid search (BM25+vector), session transcript indexing, MMR diversity, and temporal decay — all running locally with zero API keys. Use when: memory_search returns empty results, agent has poor cross-session recall, user wants to upgrade their memory system, or after a fresh OpenClaw install.

Memory Upgrade

Most OpenClaw installs have broken memory search — the memory_search tool returns empty results because no embedding provider is configured. OpenClaw auto-detects OpenAI → Google → Voyage keys; if none exist, embeddings stay disabled silently.

This skill fixes it with fully local inference. No API keys. No data leaves the machine.

Quick Start

# 1. Diagnose
bash scripts/diagnose.sh

# 2. Fix (patches openclaw.json, restart [REDACTED] after)
bash scripts/configure.sh

# 3. Restart [REDACTED]
openclaw [REDACTED] restart

# 4. Verify (waits for indexing, runs test query)
bash scripts/verify.sh

Optional Enhancements

# Organize memory files into clean directory structure
bash scripts/organize.sh

# Add YAML frontmatter tags to untagged files
bash scripts/tag.sh

What Gets Enabled

Feature	Details
Local embeddings	embeddinggemma-300m (~328MB GGUF, auto-downloads)
Hybrid search	BM25 keyword + vector semantic (70/30 weight)
Session transcripts	Past conversations become searchable
MMR diversity	Reduces duplicate/overlapping results (λ=0.7)
Temporal decay	Recent memories rank higher (30-day half-life)
Embedding cache	50k entries, avoids re-embedding unchanged text
File watcher	Auto-reindexes when memory files change

How It Works

Patches agents.defaults.memorySearch in openclaw.json
Uses node-llama-cpp (ships with OpenClaw) for local embeddings
Vector search via sqlite-vec (ships with OpenClaw)
No external dependencies required

Notes

First search after restart may be slow (model loads into memory)
Initial indexing takes 30-120s depending on file count
Embedding model runs on CPU (ARM/x86), ~768-dim vectors
Compatible with existing memory files — no migration needed

More from this repository

same repository

cron-packs

profbernardoj/everclaw-community-branches

Pre-built cron job templates for common agent automation patterns. Pick a pack, customize the placeholders, and register via OpenClaw. Categories: Essential, Family, Investor, Developer, Briefings.

2026-05-28111

mission-control

profbernardoj/everclaw-community-branches

Visual dashboard for your OpenClaw agent. Shows life goals, activity feed, key facts from memory, and project status. Auto-refreshes via daily cron job. No external dependencies — pure HTML + JSON data file.

2026-05-28111

three-shifts

profbernardoj/everclaw-community-branches

Cyclic shift execution engine. Plans tasks 3x daily (6 AM, 2 PM, 10 PM), decomposes them into granular steps, then executes via 15-minute cron cycles. Each cycle reads state files, picks the next step, executes it, writes results back. Errors are logged and skipped — never fatal. Planning uses Claude 4.6; execution uses GLM-5.

2026-05-28111

xmtp-comms-guard

profbernardoj/everclaw-community-branches

Security middleware for all XMTP communications in EverClaw. Enforces guarded client usage with validation, integrity checks, and fail-closed security policies. Integrates approval flows for sensitive operations. Use when integrating XMTP messaging, configuring communication security, or auditing guarded client enforcement.

2026-05-18111

pii-guard

profbernardoj/everclaw-community-branches

Personally identifiable information (PII) leak prevention for EverClaw. Scans outbound content against configurable PII patterns before git push, email, social media, ClawHub publishing, GitHub interactions, or any external data transmission. Provides git pre-push hooks, CLI scanning tools, and hard-block enforcement with user override capability. Use when checking content for PII before external actions, adding new protected patterns, configuring git pre-push hooks, or auditing data leak prevention.

2026-04-22111

prompt-guard

profbernardoj/everclaw-community-branches

Advanced prompt injection defense system for EverClaw with HiveFence network integration. Detects and blocks injection attacks across multiple languages (EN/KO/JA/ZH) with severity scoring, automatic logging, and configurable security policies. Includes external content detection for GitHub issues, PRs, emails, Slack, Discord, and social media. Use when processing untrusted messages, evaluating external content for threats, configuring injection detection, or integrating with the HiveFence threat intelligence network.

2026-04-22111

name	memory-upgrade
description	Diagnose and fix broken memory search in OpenClaw. Enables local embeddings, hybrid search (BM25+vector), session transcript indexing, MMR diversity, and temporal decay — all running locally with zero API keys. Use when: memory_search returns empty results, agent has poor cross-session recall, user wants to upgrade their memory system, or after a fresh OpenClaw install.

Memory Upgrade

This skill fixes it with fully local inference. No API keys. No data leaves the machine.

Quick Start

# 1. Diagnose
bash scripts/diagnose.sh

# 2. Fix (patches openclaw.json, restart [REDACTED] after)
bash scripts/configure.sh

# 3. Restart [REDACTED]
openclaw [REDACTED] restart

# 4. Verify (waits for indexing, runs test query)
bash scripts/verify.sh

Optional Enhancements

# Organize memory files into clean directory structure
bash scripts/organize.sh

# Add YAML frontmatter tags to untagged files
bash scripts/tag.sh

What Gets Enabled

Feature	Details
Local embeddings	embeddinggemma-300m (~328MB GGUF, auto-downloads)
Hybrid search	BM25 keyword + vector semantic (70/30 weight)
Session transcripts	Past conversations become searchable
MMR diversity	Reduces duplicate/overlapping results (λ=0.7)
Temporal decay	Recent memories rank higher (30-day half-life)
Embedding cache	50k entries, avoids re-embedding unchanged text
File watcher	Auto-reindexes when memory files change

How It Works

Patches agents.defaults.memorySearch in openclaw.json
Uses node-llama-cpp (ships with OpenClaw) for local embeddings
Vector search via sqlite-vec (ships with OpenClaw)
No external dependencies required

Notes

First search after restart may be slow (model loads into memory)
Initial indexing takes 30-120s depending on file count
Embedding model runs on CPU (ARM/x86), ~768-dim vectors
Compatible with existing memory files — no migration needed