- Category
- AI Agents
- Rank
- No. 1794Tools index
Previous survey · No. 1703 ·
- Pricing
- Open Source
- Type
- TOOL
- Use case
- Agent Building
- GitHub
- 6 stars
- Latest release
- v0.4.5
- Date
About
Maki is a Python framework for building multi-agent LLM applications, supporting multiple backends including Ollama, OpenAI, Anthropic, and HuggingFace. It provides a plugin system with 16 built-in tools, a workflow engine with dependency resolution and parallel execution, and a distributed layer that exposes agents over HTTP via FastAPI, letting local and remote agents be mixed in the same system.
At a glance
Maki is a Python framework for running multiple agents with local models, hosted models or a mixture of both. It is worth evaluating if you want to keep the same workflow while changing where an agent’s model runs.
Good fit
Python developers comparing deployment options for a small multi-agent workflow.
Consider something else when
Use one model client if there is no distinct work for multiple agents.
Start here
Give two agents separate roles on a synthetic task. Switch one model backend and compare the handoff and output before changing the rest of the workflow.
Cost and requirements
MIT-licensed Python framework for Python 3.10 or newer. Budget for local hardware or hosted usage according to the backends you select.
Limits to know
Provider compatibility does not guarantee identical output. Check each agent’s data path when local and hosted models run together.
Sources checked 2026-11-05. Source-based assessment.
Tags
Tech Stack
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.