arjitbhatnagar3-hue/meta-agent-learning

How arjitbhatnagar3-hue/meta-agent-learning works

Meta AgentX accepts business-analysis requests, gathers reusable profile and document context, then runs durable, multi-agent investigations that produce reviewed, evidence-backed reports. The API serves the browser and manages tasks and business data; a separate worker claims queued tasks, plans and executes specialist work, and persists outcomes. Document storage, read-only business-system connectors, and selectable LLM providers support this workflow. The README is empty, so capability coverage relies on the tree and source index; unsampled modules are represented only where their roles are explicit.

Main entry points: api.py HTTP API · worker.py Durable worker · registry.py Agent registry · specialist.py Specialist agents

Components 23

User experience

Web interface frontend/app.js

API and business data

HTTP API backend/api.py
Task and event repository backend/repository.py
Application database backend/db.py
Business context backend/repository.py
Document storage backend/storage.py

Task execution

Durable worker backend/worker.py
Task processor backend/processor.py
Dependency workflow backend/workflow.py

Agent runtime

Manager planner backend/agents/meta.py
Agent registry backend/agents/registry.py
Specialist agents backend/agents/specialist.py
Agent contracts backend/models.py
Scoped tool registry backend/tools/base.py

Providers and tools

LLM contract backend/llm/base.py
Fake LLM backend/llm/fake.py
Hugging Face provider backend/llm/huggingface.py
CRM and billing tools backend/tools/integrations.py
Business-system adapters backend/integrations.py
Enterprise tool adapters backend/tools/enterprise.py
Runtime settings backend/config.py

Other components

Business user
Supabase Storage

Connections 33

Business user → Web interface: uses
Web interface → HTTP API: sends requests
HTTP API → Task and event repository: manages tasks backend/api.py
HTTP API → Business context: manages context backend/api.py
HTTP API → Document storage: uploads and downloads backend/api.py
Task and event repository → Application database: reads and writes backend/repository.py
Business context → Application database: persists context backend/repository.py
Document storage → Supabase Storage: uploads and retrieves backend/storage.py
HTTP API → Agent registry: lists agents backend/api.py
HTTP API → Runtime settings: loads configuration backend/api.py
Durable worker → Task and event repository: claims and heartbeats backend/worker.py
Durable worker → Agent registry: builds agents backend/worker.py
Durable worker → Manager planner: constructs planner backend/worker.py
Durable worker → Dependency workflow: constructs engine backend/worker.py
Durable worker → Task processor: processes claimed tasks backend/worker.py
Task processor → Task and event repository: loads and updates backend/processor.py
Task processor → Manager planner: requests plan backend/processor.py
Task processor → Dependency workflow: executes plan backend/processor.py
Manager planner → LLM contract: requests completion backend/agents/meta.py
Manager planner → Agent contracts: validates plan backend/agents/meta.py
Dependency workflow → Specialist agents: runs assigned work backend/workflow.py
Specialist agents → Scoped tool registry: executes tools backend/agents/specialist.py
Specialist agents → LLM contract: requests completion backend/agents/specialist.py
Specialist agents → Agent contracts: produces results backend/agents/specialist.py
Agent registry → Specialist agents: creates specialists backend/agents/registry.py
Agent registry → CRM and billing tools: registers configured tools backend/agents/registry.py
Agent registry → Runtime settings: checks credentials backend/agents/registry.py
CRM and billing tools → Business-system adapters: calls adapters backend/tools/integrations.py
Business-system adapters → Runtime settings: uses credentials backend/integrations.py
Scoped tool registry → Enterprise tool adapters: supports tool contract backend/tools/enterprise.py
Fake LLM → LLM contract: implements backend/llm/fake.py
Hugging Face provider → LLM contract: implements backend/llm/huggingface.py
Hugging Face provider → Runtime settings: reads inference settings backend/llm/huggingface.py

More Python diagrams: bigballon/cifar-zoo · flymin/magicdrive-v2 · lpiccinelli-eth/unik3d · megumiss/nikkeautoscript · coding-kitties/investing-algorithm-framework

Drawn by GitDiagram on September 30, 2026 from the repository's file tree, README and source files. Read as Markdown ·