{"data":{"slug":"mantisfury-arkhammirror","name":"ArkhamMirror","tagline":"Local-first AI-powered document intelligence platform for investigative journalism","github_url":"https://github.com/mantisfury/ArkhamMirror","owner":"mantisfury","repo":"ArkhamMirror","owner_avatar_url":"https://avatars.githubusercontent.com/u/195702287?v=4","primary_language":"Python","stars":490,"forks":49,"topics":["air-gapped","data-visualization","digital-forensics","docker","document-intelligence","edge-ai","entity-extraction","intelligence-analysis","investigative-journalism","knowledge-graph","local-llm","ocr","offline-ai","open-source","osint","palantir-alternative","privacy-first","rag","self-hosted","semantic-search"],"archived":false,"github_pushed_at":"2026-01-25T07:20:43+00:00","maintenance_label":"Slowing","stars_delta_30d":6,"url":"https://www.graphcanon.com/tools/mantisfury-arkhammirror","markdown_url":"https://www.graphcanon.com/tools/mantisfury-arkhammirror.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mantisfury-arkhammirror","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mantisfury-arkhammirror","description":"Local-first AI-powered document intelligence platform for investigative journalism","homepage_url":null,"license":"MIT","open_issues":0,"watchers":6,"ai_summary":"ArkhamMirror is an open-source, privacy-first, self-hosted document intelligence platform tailored for investigative journalism, offering local LLM support and edge-ai capabilities with a focus on entity extraction, knowledge graph creation, and offline analysis.","readme_excerpt":"# Install the Frame\ncd packages/arkham-frame\npip install -e .\n\n---\n\n# Install all shards (or select specific ones)\nfor dir in ../arkham-shard-*/; do\n  pip install -e \"$dir\"\ndone\n\n---\n\n# Install spaCy model\npython -m spacy download en_core_web_sm\n\n---\n\n# Install UI dependencies\ncd ../arkham-shard-shell\nnpm install\n```\n\n---\n\n### Docker Deployment (Recommended)\n\n```bash\n\n---\n\n## Production Deployment\n\nFor production deployments with HTTPS, SHATTERED includes Traefik integration.\n\n---\n\n## Air-Gap Deployment\n\nSHATTERED is **100% air-gap capable** when configured correctly. Deploy in isolated networks with no internet access.\n\n---\n\n### Requirements\n\n- PostgreSQL 14+ with pgvector extension\n- Local LLM server (LM Studio, Ollama, or vLLM)\n- Pre-cached embedding models\n\n---\n\n# .env for air-gapped deployment\nDATABASE_URL=postgresql://user:pass@localhost:5432/shattered\n\n---\n\n## License\n\nMIT License - Copyright (c) 2025-2026 Justin McHugh\n\nSee [LICENSE](LICENSE) for details.\n\n---\n\n<div align=\"center\">\n\n**SHATTERED** - *Break documents into pieces. Reassemble the truth.*\n\nBuilt for journalists, investigators, advocates, and anyone seeking truth in documents.\n\n</div>","github_created_at":"2025-11-25T01:15:38+00:00","created_at":"2026-07-15T10:59:27.702549+00:00","updated_at":"2026-09-20T05:02:38.234645+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"air-gapped","name":"air-gapped"},{"slug":"data-visualization","name":"data-visualization"},{"slug":"digital-forensics","name":"digital-forensics"},{"slug":"docker","name":"docker"},{"slug":"document-intelligence","name":"document-intelligence"},{"slug":"edge-ai","name":"edge-ai"},{"slug":"entity-extraction","name":"entity-extraction"},{"slug":"intelligence-analysis","name":"intelligence-analysis"}],"trust":{"provenance":{"is_fork":false,"github_id":1103515339,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:02:35.728Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":237,"last_release_at":"2026-01-18T11:19:48Z","stars_delta_30d":6,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:59:29.132Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:02:36.717Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-20T05:02:36.717Z","managed_saas":false},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-20T05:02:36.717Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-20T05:02:36.717Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T05:02:36.717Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"min_ram_gb":8,"requires_docker":true},"constraints":{"min_ram_gb":8,"requires_docker":true},"when_to_use":["When handling sensitive data that requires strict privacy controls and confidentiality","For offline AI analysis and processing tasks in environments without internet access","To create detailed knowledge graphs and perform entity extraction from digital documents, images, and other media","If your workflow involves a high degree of self-hosting and customization with Python"],"when_not_to_use":["When you require cloud-based services or real-time collaboration features that are not available in a self-hosted solution","For general-purpose document intelligence tasks that do not involve investigative journalism or detailed privacy requirements","If your project's success depends on the integration with specific third-party APIs or cloud storage systems","In scenarios where continuous online data synchronization and real-time updates to central servers are essential"],"source":"enrich:decision_facts","observed_at":"2026-07-17T10:03:51.117Z"},"constraint_facets":{"min_ram_gb":8,"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Min 8 GB RAM; Requires Docker"},{"label":"Adopt for","value":"ArkhamMirror is a privacy-focused, self-hosted document intelligence platform with entity extraction and knowledge graph creation capabilities tailored for investigative journalists in air-gapped environments."}]}}