Real Skill packageSource verifiedClawHub registry

Openclaw Memory Toolkit

OpenClaw Memory Toolkit is a memory layer for AI agents. It remembers what matters across sessions: it extracts durable facts from your conversations, resolves contradictions instead of hoarding them, and lets you ask what it knew on any past date.

Identity and source

Publisher attributionStéphaneregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 61% rule confidence
Package forminstruction with code40 recorded files
Canonical sourceClawHub registryclawhub:mistermijarvis:memory-toolkit
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 10/15/2026.claude/skills/memory-health

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 10/15/2026.agents/skills/memory-health

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 10/15/2026skills/memory-health

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @mistermijarvis/memory-toolkit
clawhub inspect @mistermijarvis/memory-toolkit --version 4.0.6

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
40 / 40 inspected as text
Checked
10/15/2026, 8:40:35 AM
Scanner
0.1.3
Policy
1.0.3
3 automated findings
highInstructions or code access sensitive credential locationsscoring.py:128 · confidence 85%~/.ssh/id_rsa
highInstructions or code access sensitive credential locationsREADME.md:541 · confidence 85%~/.ssh/id_rsa
highEncoded content is decoded and executedCHANGELOG.md:902 · confidence 90%base64
3 High/Critical review queue entries
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_OBFUSCATED_EXECUTIONpending
Open human review queue →
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
5 dependency and API indicators
  • api: clawhub.ai
  • api: evil.example.com
  • api: github.com
  • api: ollama.com
  • api: www.w3.org
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
10/14/2026, 7:22:52 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:c0a088aea502ee67f42981e623b754d44d698fc910ad70cb8beec85f0c76e17c
Show up to 30 recorded paths
  • .gitignore
  • auto_archive.py
  • CHANGELOG.md
  • consolidate_advisor.py
  • CONTRIBUTING.md
  • docs/_ARCHIVED-CHANGELOG-UNRELEASED-V3.6.1.md
  • docs/AUDIT-v3.2.md
  • docs/locomo-optimization-spec.md
  • docs/SECURITY-AUDIT-NOTES.md
  • hybrid-search/auto_capture.py
  • hybrid-search/compact.py
  • hybrid-search/conflict_resolver.py
  • hybrid-search/hybrid_search.py
  • hybrid-search/llm_resolution.py
  • hybrid-search/run_tests.py
  • hybrid-search/schema.sql
  • hybrid-search/test_extract_atomic.py
  • hybrid-search/test_loopback_guard.py
  • hybrid-search/test_meta_gate.py
  • hybrid-search/test_model_resolution.py
  • hybrid-search/test_ontology_key_parity.py
  • hybrid-search/test_orphan_link.py
  • hybrid-search/transcript_adapter.py
  • mcp-server.py
  • memory-audit.py
  • memory-dedup.py
  • memory-health.py
  • migrate_ontology_subjects.py
  • migrate_subject.py
  • ontology_backfill_llm.py

Source changelog

v4.0.6 — Read-only memory access for the agent (2026-10-13) Added mcp-server.py — stdio MCP server exposing memory_query, memory_facts and memory_stats over the local hybrid search index. Read-only by construction: the server never issues a write, and diagnostics go to stderr so the JSON-RPC stream stays clean. memory-audit.py — read-only memory state report (--json, --db), SQLite opened with mode=ro. memory-dedup.py — content-hash deduplication, dry-run by default, marks duplicates with superseded_by + status='superseded' (never DELETE), guarded by --max-rows. Documentation README section 11 — the memory MCP server, with a client config example and a gateway-free smoke test. SKILL.md and CHANGELOG.md version markers synced to v4.0.6.

Release security diff

mediumCompared fixed releases 4.0.5 and 4.0.6; 0 finding and 0 permission indicators were added.

Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.

Change reasons and limitations
  • file surface changed
  • content hash changed

Observed release history

These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.

4.0.510/11/2026sha256:e9ec387aaaed9aeab584e9c622444597e377ac93843bb1149fb47ec8fa7fded2
4.0.210/10/2026sha256:3a330306bca4a8026a2ef1c6311d922afc324aed0c848ee25f6e612d30972d1a
4.0.110/10/2026sha256:8597e09318b0d79c1f42d79217b42a2ce323ac30d8bf0133f07014d35470a0a9
3.6.110/7/2026sha256:efff370d42d22c0642940a4a5c3208acadcca356436165195f5e9eebcdf83bea
3.1.110/4/2026sha256:6ebeb763ecf57aff391e662b8fa06b822b1f5eee1efd51f4f0efe6ad64c35dbe
3.0.210/3/2026sha256:a10dcb39d016fd766f22ac123e378d5cd2979440a5eed01272e399b12168938d
2.2.210/2/2026sha256:67630827fe96c0828b5298e5f96875822a48b7afb1b4b9ed0e57fb4acabbc63e
2.2.110/2/2026sha256:4fdfe6d9e9530f512846a8bdd6aa840e64ff64f7e39af0e6b508bd45ae138b9d
2.1.49/27/2026sha256:444f3f8ed9a6c31d188cbbd6ecf47bb740f101fca564e1405ed2e61f26636288
2.1.29/27/2026sha256:c64c2e6ef57fca82beb473603e7422e60c4da5d1d89627941cb4d805b312c052
2.1.18/22/2026sha256:318c105b69c516adc08ff5996dc49de775b4516e0770d60a419255af46bbb325
1.0.58/18/2026sha256:6a348ba9058f82070195a904f9b885e06b2044570eeaafc5ba71bd2375e6b6a3
1.0.38/18/2026sha256:1a0856dd21e74425c9c47012e72a65ce4522b5cdcba380c25e4a7694e23844dc
1.0.08/18/2026sha256:16f7b62844e2a6330f222bd1fb842c91e5661b271ffd732269062d516ee2e4b2
0.1.08/18/2026sha256:76fad3d40ae2f10897c646c0fc554acdcc4d44ce7c9e9cf8791669e657c27120