NLSOM

github.com/mczhuge/NLSOM AI Agent Frameworks Open-source projectOpen source

Mindstorm explores language-based societies of mind and multi-agent systems.

github.com/mczhuge/NLSOM
NLSOM homepage screenshot

About NLSOM

NLSOM is an open-source repository for natural language-based societies of mind. It organizes LLMs, neural-network experts, APIs, and role-players into societies and communities that communicate in natural language.

It can recommend communities and agents for a specified task, run a collaborative "Mindstorm" process based on mutual interviews, and assign rewards based on contribution to task completion. The source describes this as a preliminary implementation and technical extension of the NLSOM paper.

Key features

  • Agents include LLMs, neural-network experts, APIs, and role-players
  • Agents communicate with each other in natural language
  • Recommends communities and agents aligned with user goals
  • Multiple agents collaborate through mutual interviews called Mindstorm
  • New agents and components can be added in modular way
  • Rewards agents based on contribution to task completion
Best for: Researchers and developers exploring communities of language-model agents that solve tasks together.
Good for
  • Open-source code with modular structure for adding agents
  • Works with LLMs, neural-network experts, APIs, and role-players
  • Uses a shared natural-language interface between agents
Watch out for
  • Described as a preliminary solution rather than a complete system

NLSOM at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

NLSOM alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Agent Frameworks

Well-known listings from the same topic.

All 75

NLSOM FAQ

What types of agents can take part?
LLMs, neural-network-based experts, APIs, and role-players, all communicating in natural language.
How do the agents work together?
They use a collaborative Mindstorm process involving mutual interviews to solve tasks.
What does this repository include?
Autonomous selection of communities and agents, Mindstorm collaboration, and rewards for involved agents.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing