merge: integrate held feature work onto main

This commit is contained in:
2026-07-22 03:02:33 -07:00
4 changed files with 39 additions and 12 deletions
+33 -2
View File
@@ -1,6 +1,37 @@
agent
Copyright (c) 2025 Hanzo Industries, Inc.
Hanzo Agent SDK
Copyright (c) 2025 Hanzo AI, Inc.
Forked from OpenAI Agents SDK (https://github.com/openai/openai-agents-python).
Upstream release: not pinned in this repository; the source was vendored rather
than tracked as the upstream `openai-agents` package, so no upstream version
tag is recorded here.
This product includes software from OpenAI Agents SDK (https://github.com/openai/openai-agents-python), licensed under MIT:
Copyright (c) 2025 OpenAI
DEVIATIONS FROM UPSTREAM
========================
- Rebranded to the Hanzo Agent SDK: pyproject `name = "hanzoai"`, description
"Hanzo Agent SDK"; the public import namespace `agents` is retained so the
OpenAI-compatible source stays drop-in.
- Added HanzoNodeProvider (src/agents/models/hanzo_node_provider.py): a model
provider that connects directly to a Hanzo Node (hanzod) at localhost:3690,
keyed by the HANZO_NODE_API_KEY environment variable.
- Added the ZAP (Zero-copy Agent Protocol) subpackage (src/agents/zap/):
ZapClient, ZapAgent, gateway-coordinated consensus, and ZAP-gateway tool
discovery.
- Added an enhanced tool layer with MCP (Model Context Protocol) support
(src/agents/tool_enhanced.py): MCPServer, MCPTool, and MCPToolAdapter.
- Added a multi-agent network and routing subsystem (src/agents/network/):
network, node, remote, and router.
- Added an orchestration and workflow engine with UI streaming
(src/agents/orchestration/): orchestrator, executor, workflow, ui_stream.
- Added a long-term memory subsystem with vector retrieval
(src/agents/memory/): store, retriever, memory.
- Added a shared network state store (src/agents/state/): namespace,
serializer, store.
- Added optional extensions (src/agents/extensions/ with matching pyproject
extras): web3, tee, marketplace, cli, plus the zap and full bundles.
- Added Web3, TEE, and marketplace runtime dependency extras in pyproject.toml
(web3/eth-account/eth-utils, cryptography, aiohttp/redis).
+4 -8
View File
@@ -1,13 +1,9 @@
<p align="center"><img src=".github/hero.svg" alt="agent" width="880"></p>
# Hanzo AI Agent SDK
# Hanzo Agent SDK
A powerful Python framework for building AI agents and multi-agent systems with built-in orchestration.
Forked from [openai/openai-agents-python](https://github.com/openai/openai-agents-python) (MIT).
<img src="https://cdn.openai.com/API/docs/images/orchestration.png" alt="Image of the Agents Tracing UI" style="max-height: 803px;">
## ✨ Features
- 🤖 **Multi-Agent Networks**: Build systems where multiple specialized agents collaborate
@@ -36,7 +32,7 @@ Forked from [openai/openai-agents-python](https://github.com/openai/openai-agent
5. [**Tools**](docs/tools.md): Enhanced tool system with MCP support
6. [**Tracing**](docs/tracing.md): Built-in tracking and observability
Explore the [examples](examples) directory to see the SDK in action, and read our [documentation](https://openai.github.io/openai-agents-python/) for more details.
Explore the [examples](examples) directory to see the SDK in action, and read our [documentation](docs/) for more details.
Notably, our SDK [is compatible](https://openai.github.io/openai-agents-python/models/) with any model providers that support the Open AI Chat Completions API format.
@@ -49,7 +45,7 @@ python -m venv env
source env/bin/activate
```
2. Install Hanzo AI SDK
2. Install Hanzo Agent SDK
```bash
# Basic installation
@@ -248,7 +244,7 @@ The Agent SDK is designed to be highly flexible, allowing you to model a wide ra
## Tracing
The Agent SDK automatically traces your agent runs, making it easy to track and debug the behavior of your agents. Tracing is extensible by design, supporting custom spans and a wide variety of external destinations, including [Logfire](https://logfire.pydantic.dev/docs/integrations/llms/openai/#openai-agents), [AgentOps](https://docs.agentops.ai/v1/integrations/agentssdk), [Braintrust](https://braintrust.dev/docs/guides/traces/integrations#openai-agents-sdk), [Scorecard](https://docs.scorecard.io/docs/documentation/features/tracing#openai-agents-sdk-integration), and [Keywords AI](https://docs.keywordsai.co/integration/development-frameworks/openai-agent). For more details about how to customize or disable tracing, see [Tracing](http://openai.github.io/openai-agents-python/tracing).
The Agent SDK automatically traces your agent runs, making it easy to track and debug the behavior of your agents. Tracing is extensible by design, supporting custom spans and a wide variety of external destinations, including [Logfire](https://logfire.pydantic.dev/docs/integrations/llms/openai/#openai-agents), [AgentOps](https://docs.agentops.ai/v1/integrations/agentssdk), [Braintrust](https://braintrust.dev/docs/guides/traces/integrations#openai-agents-sdk), [Scorecard](https://docs.scorecard.io/docs/documentation/features/tracing#openai-agents-sdk-integration), and [Keywords AI](https://docs.keywordsai.co/integration/development-frameworks/openai-agent). For more details about how to customize or disable tracing, see [Tracing](docs/tracing.md).
## Development (only needed if you need to edit the SDK/examples)
+1 -1
View File
@@ -1,4 +1,4 @@
site_name: Hanzo AI Agent SDK
site_name: Hanzo Agent SDK
theme:
name: material
features:
+1 -1
View File
@@ -1,7 +1,7 @@
[project]
name = "hanzoai"
version = "0.0.4"
description = "Hanzo AI SDK"
description = "Hanzo Agent SDK"
readme = "README.md"
requires-python = ">=3.9"
license = "MIT"