{"data":{"slug":"justin0504-aegis","name":"Aegis","tagline":"Runtime policy enforcement for AI agents with cryptographic audit trail and human-in-the-loop approvals.","github_url":"https://github.com/Justin0504/Aegis","owner":"Justin0504","repo":"Aegis","owner_avatar_url":"https://avatars.githubusercontent.com/u/173865409?v=4","primary_language":"TypeScript","stars":340,"forks":37,"topics":["ai-agents","ai-safety","anthropic","audit-trail","langchain","llm-observability","mcp","policy-engine"],"archived":false,"github_pushed_at":"2026-09-06T03:16:51+00:00","maintenance_label":"Very active","stars_delta_30d":-27,"url":"https://www.graphcanon.com/tools/justin0504-aegis","markdown_url":"https://www.graphcanon.com/tools/justin0504-aegis.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/justin0504-aegis","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=justin0504-aegis","description":"Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.                                                                         ","homepage_url":null,"license":"MIT","open_issues":3,"watchers":20,"ai_summary":"Aegis enforces runtime policies for AI agents through a secure framework that supports anthropic alignment, audit trails, and zero-code deployment switches, suitable for various compliance requirements.","readme_excerpt":"### Deployment Mode\n\nFive ready-made templates — one click to apply on the Settings page or\nvia `POST /api/v1/config/apply-template`:\n\n| Template | L1 | L2 | L3 | Retention | Best for |\n|----------|----|----|----|-----------|----------|\n| `dev` | ✅ | ❌ | ❌ | 7 d | Local development, minimal cost |\n| `standard` | ✅ | ✅ | escalate | 90 d | Default |\n| `strict` | ✅ | ✅ | all | 180 d | High-sensitivity workloads |\n| `financial` | ✅ | ✅ | all | 7 yr (SOX) | Banking / fintech |\n| `healthcare` | ✅ | ✅ | all | 6 yr (HIPAA) | PHI handling |\n\nPer-tenant config is stored in `organizations.settings`, hot-reloads via\nan in-process ConfigBus, and every change is recorded in the admin audit\nlog.\n\n---\n\n# Public key — commit to your install machine once.\ncurl -sLo aegis-release-pubkey.pem \\\n  https://raw.githubusercontent.com/Justin0504/Aegis/main/.well-known/aegis-release-pubkey.pem\n\n---\n\n# Verify any release (npm tarball, PyPI wheel, Docker manifest).\nnode tools/release-sign/verify.mjs \\\n  --in     ./agentguard-1.2.0.tgz \\\n  --sig    ./agentguard-1.2.0.tgz.sig.json \\\n  --pubkey ./aegis-release-pubkey.pem\n\n---\n\n### Docker Compose (recommended)\n\n```bash\ndocker compose up -d                              # production\ndocker compose -f docker-compose.dev.yml up       # development (hot-reload)\n```","github_created_at":"2026-03-04T03:24:33+00:00","created_at":"2026-07-15T10:41:12.307241+00:00","updated_at":"2026-09-20T04:25:25.265195+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-safety","name":"ai-safety"},{"slug":"anthropic","name":"anthropic"},{"slug":"audit-trail","name":"audit-trail"},{"slug":"llm-observability","name":"llm-observability"},{"slug":"policy-engine","name":"policy-engine"}],"trust":{"provenance":{"is_fork":false,"github_id":1172197625,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-10T06:00:42.557Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":4,"last_release_at":"2026-06-29T08:07:55Z","stars_delta_30d":-27,"open_issues_delta_30d":0},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:41:13.554Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-10T06:00:43.022Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-10T06:00:43.022Z"},"deploy":{"source":"dockerfile:docker-compose.yml","self_host":true,"observed_at":"2026-09-10T06:00:43.022Z","managed_saas":false},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-10T06:00:43.022Z"},"has_docker":{"value":true,"source":"dockerfile:docker-compose.yml","observed_at":"2026-09-10T06:00:43.022Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-10T06:00:43.022Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You need cryptographic assurance of the audit trail to meet high-security standards.","Your project involves handling PHI or financial data needing strict compliance periods up to seven years."],"when_not_to_use":["The project does not require a zero-code deployment switch and can manage changes directly in the codebase.","Minimal regulatory requirements mean that elaborate configurations like Aegis's strict retention policies are unnecessary."],"source":"enrich:decision_facts","observed_at":"2026-07-16T19:26:56.948Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Aegis provides runtime policy enforcement for AI agents with cryptographic audit trails and human-in-the-loop approvals, supporting zero-code deployment switches suited for various compliance needs."}]}}