log-bell/avakill
View on GitHub ↗🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, and MCP. She doesn't guard. She kills.
12 ★3 forksPythonUpdated 5mo ago
Topics
ai-agentsai-safetyanthropicclaude-codecompliancecursordevtoolsfirewallguardrailslangchainllmmcpmodel-context-protocolopenaipolicy-engineprompt-injectionpythonsandboxsecuritytool-use
- Stars
- 12★
- Forks
- 3
- Language
- Python
- License
- AGPL-3.0
- Created
- 2026-02-17
- Last push
- 2026-03-10