ai-agent

Nucleoid

Name: Nucleoid
Author: NucleoidAI

Logic Language for LLMs 🌱🐋 Build World Models 🌍

772 stars33 forksRustUpdated 10/23/2026100% free · open source

What it does

Nucleoid allows you to build and interact with world models using a logic language for large language models (LLMs), enabling more structured and coherent output.

When to use it

•You need to generate text based on specific rules or constraints.
•Your application requires a deeper understanding of the relationships between entities in a domain.
•You want to build a custom AI agent that can reason about the world in a more human-like way.

Ready-to-paste prompt

./target/release/nucleoid -i 'model.nucleoid' -q 'SELECT * FROM entities WHERE type = "person";

Heads up: Nucleoid requires Rust and the Cargo package manager to be installed on your system, so ensure you have these prerequisites before attempting to build and run Nucleoid.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/nucleoid && curl -fsSL https://workflowstacks.com/api/skills/nucleoid/claude-skill -o ~/.claude/skills/nucleoid/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Nucleoid works

Codeflow

Free to inspect

Nucleoid is a medium Rust project (~13k lines across 64 code files, plus 51 test files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit this month, Apache-2.0 license, has a test suite.

Size

Medium codebase

~13k lines · 64 code files · ~2 h to skim

Setup

Some technical setup

Comfortable with a terminal? 20–40 min. Otherwise ask a dev.

Runs on

Rust

No API keys detected

Rust 100%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
src/main.rs
Where the program starts running
3
Cargo.toml
Dependencies and the commands it exposes
4
examples/_snippet.rs
A worked example — copy this to get going

What's in each folder

src/Core code — the actual logic46 files

docs/Documentation49 files

examples/Examples you can copy3 files

arc/Folder825 files

dataset/Data files29 files

tests/Tests — proof it works71 files

.github/CI / automation (GitHub Actions)22 files

READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/nucleoid && curl -fsSL https://workflowstacks.com/api/skills/nucleoid/claude-skill -o ~/.claude/skills/nucleoid/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

NucleoidAI

Language

Rust

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 303,974

superpowers

An agentic skills framework & software development methodology that works.

ai-agent★ 277,153

Track GitHub Stars with 996.ICU

ai-agent★ 253,255

Linux – 251k+ GitHub stars for building custom kernel solutions

Get the complete Linux kernel source in C, perfect for founders needing deep system control or tailored OS components.

ai-agent★ 12,950

nango

Build product integrations with AI.

ai-agent★ 7,969

kimi-code

Kimi Code CLI — The Starting Point for Next-Gen Agents

ai-agent★ 1,719

tt-metal: Accelerate AI Kernel Development with Proven Library

tt-metal gives founders a high‑performance TT‑NN operator library and low‑level kernel model to speed up GPU‑based AI workloads. Ideal for teams building LLMs, diffusion or video generation on Tenstorrent hardware. 1.7k+ GitHub stars.