{"data":{"slug":"xhmy-autodefense","name":"AutoDefense","tagline":"Multi-Agent LLM Defense against Jailbreak Attacks","github_url":"https://github.com/XHMY/AutoDefense","owner":"XHMY","repo":"AutoDefense","owner_avatar_url":"https://avatars.githubusercontent.com/u/28671304?v=4","primary_language":"Python","stars":68,"forks":20,"topics":[],"archived":false,"github_pushed_at":"2026-01-15T23:06:59+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/xhmy-autodefense","markdown_url":"https://www.graphcanon.com/tools/xhmy-autodefense.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/xhmy-autodefense","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=xhmy-autodefense","description":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","homepage_url":"https://arxiv.org/abs/2403.04783","license":"MIT","open_issues":1,"watchers":2,"ai_summary":"AutoDefense provides a framework for protecting large language models (LLMs) from jailbreak attempts using multi-agent systems.","readme_excerpt":"## Installation\n\n```bash\npip install vllm autogen pandas retry openai\n```","github_created_at":"2024-02-28T04:43:50+00:00","created_at":"2026-07-11T23:41:44.382824+00:00","updated_at":"2026-08-05T06:00:47.150397+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":"defense-mechanism","name":"defense-mechanism"},{"slug":"jailbreak-prevention","name":"jailbreak prevention"},{"slug":"large-language-models","name":"large language models"},{"slug":"llm-defense","name":"llm-defense"},{"slug":"multi-agent","name":"multi-agent"},{"slug":"python-library","name":"python library"},{"slug":"security","name":"security"}],"trust":{"provenance":{"is_fork":false,"github_id":764443584,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-05T06:00:46.383Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":201,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T23:41:45.968Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-05T06:00:46.834Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-05T06:00:46.834Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-05T06:00:46.834Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Implementing robust defenses for enterprise-level AI projects with high-security requirements","Enhancing the resilience of LLM deployments in sensitive or regulated environments"],"when_not_to_use":["Projects requiring light-weight solutions where multi-agent systems might introduce complexity overhead","Environments without access to Python and its ecosystem, as AutoDefense depends on specific Python packages"],"source":"enrich:decision_facts","observed_at":"2026-07-12T14:52:06.508Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"AutoDefense uses a multi-agent framework to mitigate jailbreak attacks on LLMs, installed via Python."}]}}