Deepmiro

What is DeepMiro?

DeepMiro simulates hundreds of AI agents to predict how communities react to events and policies. Users upload any PDF, Markdown, or text document, and DeepMiro spawns a diverse swarm of agents that debate, share, and form opinions, then delivers a calibrated prediction report.

How to use DeepMiro?

DeepMiro can be self-hosted via Docker Compose or used through the hosted option at deepmiro.org. After installation or sign‑up, use the provided tools (e.g., create_simulation, simulation_status, get_report, interview_agent) to start predictions, monitor progress, fetch reports, or chat with individual agents.

Key features of DeepMiro

• Open‑source under AGPL-3.0 license.
• Self‑hosted via Docker Compose.
• Hosted option available at deepmiro.org.
• Fully offline with Ollama support.
• Supports upload of PDF, Markdown, and text files.
• Allows interviewing any simulated agent post‑simulation.

Use cases of DeepMiro

• Predict how a community will react to a new policy.
• Simulate public opinion on a proposed event or change.
• Analyze the impact of a document by generating a diversity of viewpoints.
• Get a rapid, lightweight prediction without waiting for a full simulation.
• Review and compare past simulation results by topic.

FAQ from DeepMiro

How can I run DeepMiro locally?

DeepMiro can be self-hosted using Docker Compose. It also supports Ollama for fully offline operation.

Is there a hosted version available?

Yes, a hosted option is provided at deepmiro.org.

What file formats are supported for input?

DeepMiro supports PDF, Markdown, and plain text files.

What license does DeepMiro use?

DeepMiro is released under the AGPL-3.0 open‑source license.

Can I chat with individual agents after a simulation?

Yes, the interview_agent tool allows you to talk to any simulated agent post‑simulation.