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.
as observed 2026-10-15T18:48:12.129Z- Identifier
memory-toolkit- Source
- ClawHub
- Version observed
- 4.0.6
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-08-28T22:06:39.940Z
- Observations recorded
- 8
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 1,134
- Declared license
- MIT-0
Observation history
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"- Added three new ontology maintenance scripts: `ontology_backfill_llm.py`, `ontology_backfill_orphans.py`, and `ontology_fix_day_nodes.py`.\n- Removed the obsolete `skill-card.md | "v4.0.6 — Read-only memory access for the agent (2026-10-13)\nAdded\nmcp-server.py — stdio MCP server exposing memory_query, memory_facts\nand memory_stats over the local hybrid se |
latestVersion |
"4.0.5" | "4.0.6" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v3.6.1 — Arbiter follows the operator's real default (2026-10-06)\nFollow-up to v3.6.0. That release restored conflict arbitration but still listed glm-5.2:cloud first in PREFERRE | "- Added three new ontology maintenance scripts: `ontology_backfill_llm.py`, `ontology_backfill_orphans.py`, and `ontology_fix_day_nodes.py`.\n- Removed the obsolete `skill-card.md |
latestVersion |
"3.6.1" | "4.0.5" |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"- Added CONTRIBUTING.md to provide contribution guidelines.\n- Removed skill-card.md.\n- Version bump from 3.1.0 to 3.1.1; no functional or interface changes to the pipeline or sc | "v3.6.1 — Arbiter follows the operator's real default (2026-10-06)\nFollow-up to v3.6.0. That release restored conflict arbitration but still listed glm-5.2:cloud first in PREFERRE |
latestVersion |
"3.1.1" | "3.6.1" |
summary |
"Hybrid memory pipeline for OpenClaw agents — extraction, archiving, temporal decay scoring, consolidation, and hybrid search (FTS5 + sqlite-vec + RRF). Six standalone Python scrip | "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 inst |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v3.0.2 — Security: OLLAMA_GEN_URL bypassed the loopback guard\nRound 8 security scan of the published v3.0.0 returned 51 findings. One was real and is fixed here; the rest are the | "- Added CONTRIBUTING.md to provide contribution guidelines.\n- Removed skill-card.md.\n- Version bump from 3.1.0 to 3.1.1; no functional or interface changes to the pipeline or sc |
latestVersion |
"3.0.2" | "3.1.1" |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Round 7, from the second SkillSpector run on the published v2.2.1 (54 findings).\nMost of the report is scanner triage already covered in\ndocs/SECURITY-AUDIT-NOTES.md; one findin | "v3.0.2 — Security: OLLAMA_GEN_URL bypassed the loopback guard\nRound 8 security scan of the published v3.0.0 returned 51 findings. One was real and is fixed here; the rest are the |
latestVersion |
"2.2.2" | "3.0.2" |
summary |
"Hybrid memory pipeline for OpenClaw agents — extraction, archiving, temporal decay scoring, consolidation, and hybrid search (FTS5 + sqlite-vec + RRF). Six standalone Python scrip | "Hybrid memory pipeline for OpenClaw agents — extraction, archiving, temporal decay scoring, consolidation, and hybrid search (FTS5 + sqlite-vec + RRF). Six standalone Python scrip |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.1.4 — Allowlist/Index Agreement, Both Directions\nFollow-up found by the v2.1.3 control pass. v2.1.3 fixed an allowlist that was narrower than what was indexed; the fix then ma | "Round 7, from the second SkillSpector run on the published v2.2.1 (54 findings).\nMost of the report is scanner triage already covered in\ndocs/SECURITY-AUDIT-NOTES.md; one findin |
latestVersion |
"2.1.4" | "2.2.2" |
Fields that differed: license changelog latestVersion
| Field | Before | After |
|---|---|---|
license |
null | "MIT-0" |
changelog |
"Sensitive Data Purge\nDeleted: results/*.json (11 files), results/*.svg (9 files)\nDeleted: hybrid-search/FULL_INDEX_REPORT.md, hybrid-search/test_results.json, hybrid-search/agen | "v2.1.4 — Allowlist/Index Agreement, Both Directions\nFollow-up found by the v2.1.3 control pass. v2.1.3 fixed an allowlist that was narrower than what was indexed; the fix then ma |
latestVersion |
"2.1.1" | "2.1.4" |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.