# tophant-ai/ClawVault

OpenClaw Security Vault — Atomic "claw" control: every AI reach, within your sight.

Repository: https://github.com/tophant-ai/ClawVault
Canonical: https://ross.abutalabs.com/products/clawvault
Language: Python
License: MIT
License Family: permissive
Topics: clawdbot, clawdbot-plugin, openclaw, security
Last push: 2026-08-20T12:35:55+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 84, longevity 12
- inputs: {"age_days": 178, "days_push": 13, "days_rel": 27, "gap_med": 49, "n_releases_24m": 2}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1081, forks 38 (observed 2026-08-28T04:03:30.637191+00:00)

## What it is
ClawVault is a security vault plugin for OpenClaw AI agents that provides fine-grained, composable 'atomic' controls over what agents can access, including credentials, private files, and skills. It monitors agent interactions, intercepts sensitive data access, detects prompt injection and dangerous commands, and sends alerts via IM.

## Use cases
- prevent AI agents from accessing API keys and private files
- monitor and log how AI agents touch sensitive data
- detect prompt injection attacks and dangerous agent commands
- get notified when an agent accesses my vault assets
- set quotas and whitelists for agent model usage
- protect personal data when chatting with AI agents

## When to choose
- you run OpenClaw/clawdbot AI agents and worry about data leakage
- you need fine-grained, composable access policies for agent skills and files
- you want audit logs and real-time alerts for agent activity

## When to avoid
- you don't use OpenClaw or compatible AI agent frameworks
- you need general-purpose secrets management unrelated to AI agents
- you need a standalone enterprise DLP solution

## Facets
- artifact type: plugin
- maturity: active
- function: security, monitoring, alerting, logging, secrets-management, plugin-system
- domain: security, privacy, developer-tools
- platform: python, self-hosted, cross-platform
- tags: openclaw, ai-agent-security, prompt-injection-detection, credential-protection, data-leak-prevention, agent-monitoring, vault, ai-agents

## Member repositories
- tophant-ai/ClawVault (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:30.637191+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:51:24.291337+00:00, confidence not recorded.
  - readme: https://github.com/tophant-ai/ClawVault (fetched 2026-08-28T04:03:30.637191+00:00, sha 1ddfe483fe27)
- Data as of 2026-08-30T08:39:29.467469+00:00.