A.I.G (AI Infra Guard) vs Minimi: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of A.I.G (AI Infra Guard) and Minimi — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
A.I.G (AI Infra Guard)
Tencent Zhuque Lab
Tencent's open-source AI red teaming platform for scanning agents, agent skills, MCP servers and AI infrastructure, plus LLM jailbreak evaluation.
Key features
- Agent Skills Scan: Audits agent skill packages against a nine-category risk taxonomy aligned with the public SkillTrustBench T01-T09 classification, including detection of .pyc bytecode bypasses and charset smuggling.
- MCP Server Scan: Inspects MCP servers for threats such as tool poisoning, credential exfiltration and command injection, with tool whitelisting to prevent remote code execution during dynamic scanning.
- AI Infrastructure Vulnerability Scanning: Checks deployed AI components against a library that has grown to roughly 130 components and over 2,000 CVE rules, covering frameworks such as llama.cpp.
- Jailbreak Evaluation: Runs single-turn jailbreak operators plus multi-turn attack techniques including Many-Shot, PAIR, GOAT and ActorAttack to measure a model's resistance.
- Agent Scan with OWASP Coverage: Assesses running agents using OWASP-derived skills and web exfiltration detection, with a dedicated agent red team skill for comprehensive assessment.
- Standalone Scanner CLIs: skill-scan, mcp-scan and agent-scan each install as an independent command-line tool so scans can be wired directly into enterprise CI/CD pipelines.
- Docker Deployment with Web UI: Deploy the full platform with Docker on 4GB+ RAM and reach the web interface at localhost:8088, or use a one-click install script or a source build.
- AI Security Skill Market: A catalog of official security scanning skills, with the frontend fully open-sourced and integration available from OpenClaw chat via the aig-scanner skill.
Best for
- Pre-Deployment Agent Audit: Scan an internally built agent and its skill bundle for prompt injection, exfiltration and privilege risks before it is released to staff.
- MCP Supply Chain Review: Vet third-party MCP servers for tool poisoning and credential exfiltration before connecting them to production assistants.
- CI/CD Security Gate: Run skill-scan as a standalone CLI on every pull request so risky agent skills fail the build rather than shipping.
- Model Safety Benchmarking: Measure how a deployed LLM holds up against single and multi-turn jailbreak techniques before and after guardrail changes.
- AI Infrastructure Patch Triage: Inventory AI serving components and match them against the CVE rule library to prioritise which hosts need patching.
- Security Research and Reporting: Use the open scan engines and SkillTrustBench alignment as a reproducible basis for internal or published AI security research.
Minimi
Shram
Minimi is an ambient memory Mac app that quietly captures tabs, documents, calls, and Slack threads to provide context for Claude.
Key features
- Ambient Memory Capture: Continuously records user activity on macOS — including open browser tabs, documents, calls, and Slack threads — to create a persistent context layer.
- Claude Context Integration: Supplies collected context to Claude to improve response relevance and maintain continuity across conversations.
- Background Mac App: Runs quietly on the Mac, minimizing user friction while maintaining an ongoing record of interactions across apps.
- Meeting Notetaker Support: Enables creation of live artifacts such as Mini-scribe, a Granola-style AI meeting notetaker that operates entirely on Minimi memory.
- Inbox for Incomplete Conversations: Acts as an AI inbox that surfaces and preserves incomplete or ongoing conversations for follow-up and continuity.
- Context-First Responses: Ensures every Claude response can start with rich, user-specific context gathered from recent activity.
- Continuous background capture of user activity (browser tabs, documents, calls, Slack threads)
- Centralized ambient memory to provide context to Claude conversations
- Inbox-style management for incomplete or ongoing conversations
- Enables context-rich downstream tools (e.g., meeting notetakers like "Mini-scribe")
- Quiet/background operation aimed at minimizing user friction
Best for
- Enhancing Claude chat quality by pre-loading recent tabs, documents, and messages so answers reflect the user's current context and work.
- Automated meeting notetaking: running a Mini-scribe artifact that uses Minimi memory to generate meeting notes and action items without manual setup.
- Managing an inbox of incomplete or pending conversations, enabling easier follow-up and continuity across asynchronous threads.
- Research and writing assistance: providing the assistant with the user's active documents and tabs so drafting and summarization use accurate source context.
- Cross-app context retrieval: surfacing recent Slack discussions, call notes, and opened documents to inform decisions and reduce repetitive explanations.
- Provide persistent context to Claude for better, context-aware assistant responses
- Automatically capture meeting context to power AI meeting notes and summaries
- Aggregate fragmented conversation threads (email, Slack, docs) into a unified inbox of incomplete tasks
- Recall past interactions and documents when composing responses or continuing conversations
- Power custom Claude-based agents that rely on personal desktop context