mirror of https://github.com/hanzoai/agents.git synced 2026-10-30 18:48:36 +00:00

Files

T

zeekayandGitHub 5b5cf9e9db feat: merge AgentField control plane + SDKs as Hanzo Agents (#1 )

Transforms hanzoai/agents from a marketplace config repo into a full
agent orchestration platform by merging the AgentField infrastructure:

- Go control plane (K8s-like agent orchestration, service mesh, DAG workflows)
- Python SDK (FastAPI-based agent framework, LiteLLM, memory, DID/VC)
- TypeScript SDK (@hanzo/agents - Vercel AI SDK, MCP, workflows)
- Go SDK (idiomatic agent builder + client)
- React 19 embedded dashboard (XyFlow DAGs, Recharts, Radix UI)
- Docker/K8s/Helm deployment configs
- Examples: hello world, deep research, RAG, simulation, benchmarks
- Functional test suite across Python/Go/TypeScript

All references rebranded: AgentField → Hanzo Agents
- Module: github.com/hanzoai/agents/control-plane
- Python: hanzo_agents
- TypeScript: @hanzo/agents
- Go: github.com/hanzoai/agents/sdk/go
- Env vars: HANZO_AGENTS_*
- Config: hanzo-agents.yaml

Previous marketplace configs moved to config/ directory.

2026-02-09 18:53:09 -08:00

2.9 KiB

Raw Permalink Blame History

Deep Research Agent

A research agent that uses recursive planning to break down research questions into subtasks, forms a topological graph for parallel execution, deduplicates tasks, and synthesizes comprehensive reports.

Features

Recursive Planning – Breaks down questions into subtasks with configurable depth
Task Deduplication – Merges redundant tasks
Smart Search Strategy – Decides synthesis-only vs enhanced search for parent tasks
Topological Execution – Parallel execution with dependency management
Web Search – Tavily API integration with citation tracking

Quick Start

1. Install & Setup

pip install -r examples/python_agent_nodes/deep_research/requirements.txt
export TAVILY_API_KEY="your-tavily-api-key"

2. Run Agent

python examples/python_agent_nodes/deep_research/main.py

3. Execute Research

curl -X POST http://localhost:8080/reasoners/planning_execute_deep_research \
  -H "Content-Type: application/json" \
  -d '{
    "research_question": "What is Hanzo Agents.ai?",
    "max_depth": 3,
    "max_tasks_per_level": 5
  }'

Architecture

Plan Creation – Recursively breaks question into distinct tasks
Deduplication – Merges redundant tasks
Dependency Identification – Maps task dependencies
Execution – Topological order:
- Leaf tasks → web search
- Parent tasks → synthesis or enhanced search (with context)
Synthesis – Final report from all findings

Endpoints

Main

/reasoners/planning_execute_deep_research – Complete workflow (recommended)
- Params: research_question, max_depth (default: 3), max_tasks_per_level (default: 5)

Planning

/reasoners/planning_create_research_plan – Create plan only
/reasoners/planning_deduplicate_tasks – Deduplicate tasks
/reasoners/planning_identify_dependencies – Identify dependencies
/reasoners/planning_decide_search_strategy – Decide search strategy

Research

/reasoners/research_execute_research_task – Execute leaf task (search)
/reasoners/research_execute_research_task_with_context – Execute with dependency context
/reasoners/research_synthesize_from_dependencies – Synthesize from children

Task Types

Leaf Tasks (no deps) → Web search
Parent Tasks (has deps) → Synthesis-only or enhanced search with context

Environment Variables

Variable	Description	Default
`TAVILY_API_KEY`	Tavily API key (required)	-
`HANZO_AGENTS_SERVER`	Control plane URL	`http://localhost:8080`
`AI_MODEL`	LLM model	`openrouter/deepseek/deepseek-v3.1-terminus`

2.9 KiB Raw Permalink Blame History Unescape Escape