{"data":{"slug":"killertcell428-aigis","name":"aigis","tagline":"Deterministic zero-dependency Python firewall for AI agents","github_url":"https://github.com/killertcell428/aigis","owner":"killertcell428","repo":"aigis","owner_avatar_url":"https://avatars.githubusercontent.com/u/247917039?v=4","primary_language":"Python","stars":54,"forks":8,"topics":["ai-agent","ai-security","audit-log","claude-code","compliance","cybersecurity","firewall","guardrails","jailbreak-detection","llm","mcp","open-source","owasp","prompt-injection","python","tool-poisoning"],"archived":false,"github_pushed_at":"2026-09-08T22:41:48+00:00","maintenance_label":"Very active","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/killertcell428-aigis","markdown_url":"https://www.graphcanon.com/tools/killertcell428-aigis.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/killertcell428-aigis","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=killertcell428-aigis","description":"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.","homepage_url":"https://pypi.org/project/pyaigis/","license":"Apache-2.0","open_issues":13,"watchers":1,"ai_summary":"Provides security functionalities such as compliance enforcement and protection against various threats like memory poisoning and prompt injection.","readme_excerpt":"## Quick Start\n\nFor developers building or running agents, the library is two lines and needs no config, API keys, or Docker:\n\n```bash\npip install pyaigis\n```\n\n```python\nfrom aigis import Guard\n\nguard = Guard()\n\n---\n\n## License\n\nApache 2.0 — free for personal and commercial use. See [LICENSE](LICENSE).\n\n---\n\n<p align=\"center\">\n  <img src=\"https://raw.githubusercontent.com/killertcell428/aigis/master/images/aigis_icon_v01.jpg\" alt=\"Aigis\" width=\"120\" /><br />\n  <sub>Named after the Aegis, the shield of Zeus. AI + Aegis = Aigis.</sub>\n</p>","github_created_at":"2026-04-11T02:56:13+00:00","created_at":"2026-07-15T10:45:05.522665+00:00","updated_at":"2026-09-20T04:26:33.368491+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"ai-agent","name":"ai-agent"},{"slug":"ai-security","name":"ai-security"},{"slug":"compliance","name":"compliance"},{"slug":"cybersecurity","name":"cybersecurity"},{"slug":"firewall","name":"firewall"},{"slug":"guardrails","name":"guardrails"},{"slug":"jailbreak-detection","name":"jailbreak-detection"},{"slug":"llm","name":"llm"}],"trust":{"provenance":{"is_fork":false,"github_id":1207506427,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-13T06:00:50.907Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":2,"days_since_push":4,"last_release_at":"2026-08-24T05:12:24Z","stars_delta_30d":1,"open_issues_delta_30d":2},"security_summary":{"status":"ok","scanner":"mcp_manifest@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:45:07.288Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-13T06:00:51.345Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-13T06:00:51.345Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-13T06:00:51.345Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-13T06:00:51.345Z"},"languages":{"value":["python","javascript"],"source":"github.language+package.json+pyproject.toml","observed_at":"2026-09-13T06:00:51.345Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-13T06:00:51.345Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-13T06:00:51.345Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When your AI application requires robust security measures with minimal setup complexity","For ensuring compliance across diverse regions including US, CN, JP, EU","If you need a solution without API keys or additional dependencies"],"when_not_to_use":["If your project strictly avoids adding third-party libraries","When a full-fledged security solution with comprehensive features is necessary over minimal dependency footprint"],"source":"enrich:decision_facts","observed_at":"2026-07-16T19:03:55.721Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"aigis is a deterministic zero-dependency Python firewall for AI agents offering protection against threats like memory poisoning and prompt injection with no external dependencies or complex configurations."}]}}