{"data":{"slug":"maziyarpanahi-openmed","name":"openmed","tagline":"Local-first healthcare AI for clinical NER and HIPAA PII de-identification.","github_url":"https://github.com/maziyarpanahi/openmed","owner":"maziyarpanahi","repo":"openmed","owner_avatar_url":"https://avatars.githubusercontent.com/u/5762953?v=4","primary_language":"Python","stars":5346,"forks":680,"topics":["android","clinical-nlp","healthcare","hipaa","ios","javascript","llm","local-llm","mlx","ner","nlp","on-device","on-premise","pii","pii-detection","python","skills","sovereign-ai","swift","swiftui"],"archived":false,"github_pushed_at":"2026-09-19T13:42:26+00:00","maintenance_label":"Very active","stars_delta_30d":372,"url":"https://www.graphcanon.com/tools/maziyarpanahi-openmed","markdown_url":"https://www.graphcanon.com/tools/maziyarpanahi-openmed.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/maziyarpanahi-openmed","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=maziyarpanahi-openmed","description":"Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+ medical models, 21 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0","homepage_url":"https://openmed.life/","license":"Apache-2.0","open_issues":517,"watchers":23,"ai_summary":"Provides over 1,000 medical models in 12 languages, supporting both Apple MLX and Python, with full on-device execution to ensure patient data remains within your network at all times.","readme_excerpt":"# or with Docker\ndocker build -t openmed:local .\ndocker run --rm -p 8080:8080 -e OPENMED_PROFILE=prod openmed:local\n```\n\nExample output:\n\n```text\nINFO:     Uvicorn running on http://0.0.0.0:8080\n```\n\n```bash\ncurl -X POST http://127.0.0.1:8080/pii/extract \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"text\":\"Paciente: Maria Garcia, DNI: 12345678Z\",\"lang\":\"es\"}'\n```\n\nAbbreviated example response:\n\n```json\n{\n  \"text\": \"Paciente: Maria Garcia, DNI: 12345678Z\",\n  \"entities\": [\n    {\"text\": \"Maria Garcia\", \"label\": \"NAME\", \"confidence\": 0.99, \"start\": 10, \"end\": 22},\n    {\"text\": \"12345678Z\", \"label\": \"ID\", \"confidence\": 0.98, \"start\": 29, \"end\": 38}\n  ],\n  \"model_name\": \"OpenMed/privacy-filter-multilingual\"\n}\n```\n\n**Model lifecycle and service controls:** free memory on demand with\n`GET /models/loaded`, `POST /models/unload`, and a `keep_alive` idle window;\nv1.8 also includes API-key/JWT auth, no-PHI request logging, tracing, gRPC,\nasync jobs, webhooks, warm pools, dynamic batching, request coalescing, rate\nand concurrency limits, `/livez`, `/readyz`, and opt-in metrics:\n\n```bash\nOPENMED_SERVICE_KEEP_ALIVE=10m uvicorn openmed.service.app:app --host 0.0.0.0 --port 8080\ncurl -X POST http://127.0.0.1:8080/models/unload -H \"Content-Type: application/json\" -d '{\"all\":true}'\n```\n\nExample response:\n\n```json\n{\n  \"unloaded\": true,\n  \"released\": {\"models\": 1, \"tokenizers\": 1, \"pipelines\": 1},\n  \"active_models\": {}\n}\n```\n\nSee the full [REST service guide](docs/rest-service.md).\n\n---\n\n---\n\n## License\n\nThe OpenMed SDK source is released under the [Apache-2.0 License](LICENSE). Third-party asset notices are recorded in [NOTICE](NOTICE).","github_created_at":"2025-10-04T15:13:34+00:00","created_at":"2026-07-15T10:58:08.40816+00:00","updated_at":"2026-09-20T04:59:08.227361+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"clinical-nlp","name":"clinical-nlp"},{"slug":"healthcare","name":"healthcare"},{"slug":"hipaa","name":"hipaa"},{"slug":"ios","name":"ios"},{"slug":"mlx","name":"mlx"},{"slug":"ner","name":"ner"},{"slug":"nlp","name":"nlp"},{"slug":"on-device","name":"on-device"}],"trust":{"provenance":{"is_fork":false,"github_id":1069760430,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T04:59:05.671Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":11,"days_since_push":0,"last_release_at":"2026-09-15T13:22:38Z","stars_delta_30d":372,"open_issues_delta_30d":-160},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:58:09.649Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T04:59:06.706Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-20T04:59:06.706Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T04:59:06.706Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T04:59:06.706Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-20T04:59:06.706Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T04:59:06.706Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need full data sovereignty with no cloud dependency","For use-cases with strict local-first execution mandates","If HIPAA-compliant PII de-identification is a requirement"],"when_not_to_use":["Avoid if flexible model training and updates from the cloud are preferred","Not suitable for environments without powerful edge devices","If a broad ecosystem of AI tools beyond clinical NER is needed"],"source":"enrich:decision_facts","observed_at":"2026-07-16T19:59:52.144Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"openmed supplies localized AI for clinical NER tasks and HIPAA-compliant PII de-identification across 12 languages with over 1000 models, operable on-device in Python or Apple MLX."}]}}