Metadata-Version: 2.4
Name: mandri
Version: 0.1.0a1
Summary: Turn agents into a team
Project-URL: Homepage, https://github.com/mandri-labs/mandri
Project-URL: Repository, https://github.com/mandri-labs/mandri
Project-URL: Issues, https://github.com/mandri-labs/mandri/issues
Author-email: Mandri Labs <labs@mandri.io>
License-Expression: Apache-2.0
License-File: LICENSE
Keywords: agents,ai,orchestration
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.13
Classifier: Typing :: Typed
Requires-Python: >=3.13
Requires-Dist: agent-client-protocol>=0.11.0
Requires-Dist: aiohttp>=3.14.3
Requires-Dist: charset-normalizer>=3.4.9
Requires-Dist: httpx>=0.28.1
Requires-Dist: mcp<2,>=1.12
Requires-Dist: packaging>=26.0
Requires-Dist: rich>=15.0.0
Requires-Dist: starlette>=1.3.1
Requires-Dist: textual>=8.2.8
Requires-Dist: uvicorn>=0.51.0
Description-Content-Type: text/markdown

> [!WARNING]
> Mandri is in alpha - expect bugs and breaking changes.

# Mandri

Mandri is an open, local-first orchestrator for autonomous agents.

For a simple task, Mandri can delegate the work to a single agent. If that
agent gets stuck, it can bring in another agent with a different model,
runtime, or set of capabilities.

For complex tasks, Mandri coordinates multiple specialist agents, allowing
them to exchange requests, findings, and results while working toward the
same outcome.

## Built on proven agents

Mandri does not try to rebuild coding, browser, or terminal agents from
scratch.

It orchestrates agents that already know how to do their job, such as Claude
Code, Codex, OpenCode, and other specialized runtimes, and gives them a way to
delegate work, exchange context, and coordinate around the same task.

Each agent keeps its own tools, execution loop, context, permissions, and
strengths.

## Bring your own models

Mandri separates the agent runtime from the language model behind it.

Through its model gateway, a compatible agent can use the provider or model
selected by the user, whether it runs locally, through a cloud API, or behind
any OpenAI-compatible endpoint.

## Lean by design

Mandri uses as few dependencies as possible.

It is not an all-in-one agent framework, a workflow platform, or a replacement
for every tool it connects to. Its purpose is narrower: delegate work,
coordinate agents, route communication, and keep the user in control.

## License

Mandri is licensed under the Apache License 2.0.
