TheBotique

ai-guardian

Use this skill whenever the user needs to observe or govern on-endpoint local LLMs running on Ollama, llama.cpp (llama-server), LM Studio, or a local single-node vLLM — inventory installed/running models with an allow/deny verdict (shadow-AI detection), inspect VRAM residency, model license/params/c

as observed 2026-11-08T17:43:36.701Z
Identifier
ai-guardian
Source
ClawHub
Version observed
0.14.1
Source repository
not published
Repository observation
No source repository listed
First observed here
2026-08-28T22:54:43.883Z
Observations recorded
7
Installs (reported upstream)
0
Weekly downloads (upstream)
1,949
Declared license
MIT-0

Observation history

2026-11-08T17:43:36.701Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "- Added guidance that real writes require durable audit intent; reads and previews may continue if audit storage fails.\n- Removed the `skill-card.md` file." "- Updated the display name to “Local LLM Guard for Ollama / llama.cpp.”\n- Removed `skill-card.md`."
latestVersion "0.14.0" "0.14.1"
2026-10-30T08:44:46.517Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "- Removed the skill-card.md file.\n- No changes to features or functionality; documentation file only." "- Added guidance that real writes require durable audit intent; reads and previews may continue if audit storage fails.\n- Removed the `skill-card.md` file."
latestVersion "0.13.0" "0.14.0"
2026-10-15T18:48:12.129Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "ai-guardian v0.11.3\n\n- Removed the file: skill-card.md\n- No added features or functional changes in this release\n- The skill continues to provide local LLM observability and g "- Removed the skill-card.md file.\n- No changes to features or functionality; documentation file only."
latestVersion "0.11.3" "0.13.0"
2026-09-17T19:21:46.989Z

Fields that differed: license description

FieldBeforeAfter
license null "MIT-0"
description "Use this skill whenever the user needs to observe or govern on-endpoint local LLMs running on Ollama, llama.cpp (llama-server), LM Studio, or a local single-node vLLM — inventory null
2026-09-15T17:18:40.325Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "- Documentation updated in SKILL.md, including Quick Install and plugin instructions.\n- References to OpenClaw plugin install updated from clawhub:@aiops-tools/ai-guardian to cla "ai-guardian v0.11.3\n\n- Removed the file: skill-card.md\n- No added features or functional changes in this release\n- The skill continues to provide local LLM observability and g
latestVersion "0.11.2" "0.11.3"
2026-09-12T14:17:54.398Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "ai-guardian 0.10.0\n\n- Added support for an additional tool, increasing the total to 21 MCP tools.\n- Updated documentation to reflect features for a transparent capture proxy (v "- Documentation updated in SKILL.md, including Quick Install and plugin instructions.\n- References to OpenClaw plugin install updated from clawhub:@aiops-tools/ai-guardian to cla
latestVersion "0.10.0" "0.11.2"

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.