How abhinavprkash/fetch-health works
Fetch Health is an educational donor/recipient matching simulator: public Fetch agents route requests through a selective-activation harness to a FastAPI gateway, which manages uploads and runs, processes case information, retrieves candidates, and returns transparent matching results. Separate data tools prepare profile and artifact datasets for use by the gateway. The README documents the top-level boundaries; source-index references and excerpts support selected internal links. Unsampled route and worker details are shown only where documented, not inferred.
Main entry points: main.py FastAPI gateway · candidate_store.py Candidate store · harness.py Agent harness · run_service.py Run orchestration
Components 30
Agent access
- Capability agents
swarm/generated - Agent harness
swarm/harness.py - Agent activation
swarm/activation_manager.py
Gateway workflow
- FastAPI gateway
backend/app/main.py - Agent requests
backend/app/routes/agents.py - Case uploads
backend/app/routes/uploads.py - Run lifecycle
backend/app/routes/runs.py - Profiles
backend/app/routes/profiles.py - Education API
backend/app/routes/edu.py - Run orchestration
backend/app/services/run_service.py - Document analysis
backend/app/processors/document.py - Image video analysis
backend/app/processors - Donor matching
backend/app/services/donor_matching.py - Candidate retrieval
backend/app/services/retrieval.py - Candidate store
backend/app/repositories/candidate_store.py - Profile store
backend/app/repositories/profile_store.py - Run store
backend/app/repositories/run_store.py
Data preparation
- Dataset pipeline
data/data_pipeline/src/main.py - Transplant data factory
data/transplant_data_factory/src/main.py - Profile builder
data/transplant_data_factory/src/builders/profile_builder.py
Local Bureau
- Local Bureau
local_agents/bureau.py - Document worker
local_agents/agents/document_parser.py
Shared integrations
- LLM integration
backend/app/integrations/llm.py - Audio transcription
backend/app/integrations/audio.py - Edu diagrams
backend/app/integrations/imagegen.py
Other components
- ASI:One user
- Redis Stack
- Claude / ASI:One
- Deepgram
- Midjourney proxy
Connections 36
- ASI:One user → Agent harness: submits tasks
README.md - Agent harness → Capability agents: routes capabilities
README.md - Agent harness → Agent activation: activates agents
README.md - Agent harness → FastAPI gateway: forwards requests
README.md - Capability agents → FastAPI gateway: uses gateway endpoints
README.md - FastAPI gateway → Agent requests: registers routes
backend/app/main.py - FastAPI gateway → Case uploads: registers routes
backend/app/main.py - FastAPI gateway → Run lifecycle: registers routes
backend/app/main.py - FastAPI gateway → Profiles: registers routes
backend/app/main.py - FastAPI gateway → Education API: registers routes
backend/app/main.py - Run lifecycle → Run orchestration: manages runs
- Run orchestration → Run store: updates run state
backend/app/services/run_service.py - Run orchestration → Donor matching: requests matches
backend/app/services/run_service.py - Run orchestration → Document analysis: coordinates processing
- Case uploads → Document analysis: dispatches document analysis
- Case uploads → Image video analysis: dispatches media analysis
- Donor matching → Candidate retrieval: retrieves candidates
- Candidate retrieval → Candidate store: searches candidates
backend/app/services/retrieval.py - Profiles → Candidate store: accesses candidates
backend/app/routes/profiles.py - Profiles → Profile store: uses profile storage
- FastAPI gateway → Candidate store: initializes store
backend/app/main.py - FastAPI gateway → Profile store: initializes store
backend/app/main.py - FastAPI gateway → Run store: initializes store
backend/app/main.py - Candidate store → Redis Stack: stores and searches
- Dataset pipeline → Transplant data factory: shares profile data conventions
- Transplant data factory → Profile builder: builds profiles
data/transplant_data_factory/src/main.py - Transplant data factory → Candidate store: exports candidate data
- Local Bureau → Document worker: registers worker
local_agents/bureau.py - Document worker → FastAPI gateway: gateway performs extraction
local_agents/agents/document_parser.py - Document analysis → LLM integration: uses extraction model
- LLM integration → Claude / ASI:One: calls provider
backend/app/integrations/llm.py - LLM integration → ASI:One user: calls ASI:One
- Audio transcription → Deepgram: transcribes media
README.md - Image video analysis → Audio transcription: uses transcription
- Education API → Edu diagrams: requests diagrams
- Edu diagrams → Midjourney proxy: generates diagrams
README.md