killertcell428

killertcell428/aigis

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a generated IT-approval pack. Zero-dependency Python OSS.

54 stars 8 forks 54 watchers Python Apache License 2.0
ai-agent ai-security audit-log claude-code compliance cybersecurity firewall guardrails jailbreak-detection llm mcp open-source owasp prompt-injection python tool-poisoning
View on GitHub Website
5 Open Issues Need Help Last updated: Sep 2, 2026

Open Issues Need Help

View All on GitHub
[Feature] SIEM forwarder: durable on-disk queue spool (follow-up to #98 foundation) 20 days ago
enhancement help wanted
killertcell428/aigis
54

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a generated IT-approval pack. Zero-dependency Python OSS.

Python
#ai-agent#ai-security#audit-log#claude-code#compliance#cybersecurity#firewall#guardrails#jailbreak-detection#llm#mcp#open-source#owasp#prompt-injection#python#tool-poisoning
[Perf] Latency cliff: repeated-token inputs (token_exhaustion) cost 2-3s per scan (DoS-adjacent) 3 months ago
bug help wanted performance
killertcell428/aigis
54

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a generated IT-approval pack. Zero-dependency Python OSS.

Python
#ai-agent#ai-security#audit-log#claude-code#compliance#cybersecurity#firewall#guardrails#jailbreak-detection#llm#mcp#open-source#owasp#prompt-injection#python#tool-poisoning
[Feature] Wire SignedAuditLog into the Claude Code hook path by default for --policy enterprise 3 months ago
enhancement help wanted
killertcell428/aigis
54

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a generated IT-approval pack. Zero-dependency Python OSS.

Python
#ai-agent#ai-security#audit-log#claude-code#compliance#cybersecurity#firewall#guardrails#jailbreak-detection#llm#mcp#open-source#owasp#prompt-injection#python#tool-poisoning
[benchmark] Reproducible comparison vs LLM Guard / Guardrails AI / NeMo Guardrails 4 months ago
documentation enhancement help wanted
killertcell428/aigis
54

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a generated IT-approval pack. Zero-dependency Python OSS.

Python
#ai-agent#ai-security#audit-log#claude-code#compliance#cybersecurity#firewall#guardrails#jailbreak-detection#llm#mcp#open-source#owasp#prompt-injection#python#tool-poisoning
[integration] LangGraph: ship AigisGuardNode recipe + working example 4 months ago
enhancement help wanted
killertcell428/aigis
54

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a generated IT-approval pack. Zero-dependency Python OSS.

Python
#ai-agent#ai-security#audit-log#claude-code#compliance#cybersecurity#firewall#guardrails#jailbreak-detection#llm#mcp#open-source#owasp#prompt-injection#python#tool-poisoning