LucidAkshay/kavach
Tactical AI Workspace Monitor & EDR
This tool helps safeguard your local computer systems from unintended or malicious actions by autonomous AI agents and large language models (LLMs) running on your machine. It takes your designated project workspaces as input and provides real-time monitoring, alerts, and automatic remediation actions to prevent data loss or exfiltration. Security professionals, data scientists, and developers working with local AI agents would find this indispensable.
189 stars.
Use this if you are running AI agents or local LLMs on your machine and are concerned about them accidentally deleting files, overwriting code, or leaking sensitive information.
Not ideal if you need kernel-level system call blocking for a true zero-trust sandbox environment, as this feature is planned for a future release.
Stars
189
Forks
32
Language
TypeScript
License
GPL-3.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/LucidAkshay/kavach"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
Nebulock-Inc/agentic-threat-hunting-framework
ATHF is a framework for agentic threat hunting - building systems that can remember, learn, and...
AgentSeal/agentseal
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor...
cosai-oasis/secure-ai-tooling
The CoSAI Risk Map is a framework for identifying, analyzing, and mitigating security risks in...
HeadyZhang/agent-audit
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis....
oasm-platform/open-asm
Open-source platform for cybersecurity Attack Surface Management (OASM).