<!-- mcp-name: io.github.eidetic-works/nucleus -->

.brain — the portable decision log

The portable decision log your AI tools all read. One MCP server. Any AI tool. Plain files.

Every AI coding session starts by re-explaining context the last session already knew. .brain is a folder in your repo that Claude Code, Cursor, and Codex all read via one MCP server. Decisions, policies, plans — written once, remembered across every session and every tool.

MIT licensed. File-based (plain JSON + markdown). No embeddings. No vendor lock-in.

Also included: nucleus-rabbithole

nucleus-mcp ships a second, fully independent tool: nucleus-rabbithole, a rabbit-hole depth tracker for focus-prone developers.

It gives your AI a push/pop depth stack, a context-switch thrash detector, an open-loop externaliser, and a weekly review — all backed by local SQLite, no network, no daemon.

# Already installed with nucleus-mcp — just run:
nucleus-rabbithole

Claude Code .mcp.json snippet:

{
  "mcpServers": {
    "nucleus-rabbithole": {
      "command": "nucleus-rabbithole",
      "args": []
    }
  }
}

Full documentation: docs/RABBITHOLE.md

Three Frontiers

The core loop that makes AI reliability compound over time:

  GROUND              ALIGN               COMPOUND
  ──────              ─────               ────────
  Machine verifies    Human corrects      System learns

  AI writes code  →  You fix a mistake →  Delta recorded
  GROUND checks   →  Verdict stored    →  DPO pair created
  Receipt logged  →  Event emitted     →  Training data grows
       │                   │                    │
       └───────────────────┴────────────────────┘
                    Reliability improves

GROUND — 5-tier execution verification. Syntax, imports, tests, runtime. Goes outside the formal system to check the AI's work.

ALIGN — One-call corrections. nucleus_align(action="correct", params={context, correction}). Each correction automatically records a verdict, creates a training pair, and emits an event.

COMPOUND — Deltas measure the gap between intent and reality. Recurring patterns become strategy. Negative deltas become training signal.

Every tool response shows frontier health:

[frontiers: GROUND 42 | ALIGN 12 | COMPOUND 28]

Quick Start

Option A — No install (ChatGPT, Claude, Perplexity):

Add https://relay.nucleusos.dev/mcp as a remote MCP server in your platform's connector settings. That's it — your AI now has persistent memory.

Option B — Local install (Cursor, Windsurf, Claude Desktop):

pip install nucleus-mcp
nucleus init --recipe founder

Two commands. Nucleus is running. AI outputs are now verified. nucleus init auto-configures your MCP client — just restart it.

What It Does

114 MCP tools across 13 facades:

• GROUND — Execution verification (5 tiers: diff, syntax, imports, tests, runtime)
• ALIGN — Human corrections (verdict + delta + DPO + event in one call)
• Memory — Engrams that persist across sessions. Write once, recall forever.
• Sessions — Save context, resume later. Session arc shows your last 3 sessions.
• Tasks — Priority queue with escalation, HITL gates, and heartbeat monitoring.
• Governance — Kill switch, compliance configs (EU DORA, MAS TRM, SOC2), audit trails.
• Orchestration — Agent slots, multi-brain sync, task dispatch.
• Archive — Training pipeline (SFT + DPO), delta tracking, frontier health dashboard.

Benchmark: decision-retention-evals — does your AI agent remember why the code is the way it is?

Nucleus Pro

Everything above is free (MIT). Nucleus Pro adds verifiable governance:

nucleus trial                              # 14-day free trial
nucleus compliance-check                   # Score your AI governance
nucleus audit-report --signed -o report.html  # Cryptographically signed report

$19/month or $149/year — nucleusos.dev/pricing

Install

One-Click

pip / npx

pip install nucleus-mcp

Or use npx (zero Python setup required):

npx -y nucleus-mcp

Configure Your MCP Client

Claude Desktop / Cursor / Windsurf

Add to your MCP config (claude_desktop_config.json or equivalent):

{
  "mcpServers": {
    "nucleus": {
      "command": "npx",
      "args": ["-y", "nucleus-mcp"]
    }
  }
}

<details> <summary>Alternative: use pip install directly</summary>

{
  "mcpServers": {
    "nucleus": {
      "command": "python3",
      "args": ["-m", "mcp_server_nucleus"],
      "env": {
        "NUCLEUS_BRAIN_PATH": "/path/to/your/project/.brain"
      }
    }
  }
}

</details>

Claude Code

Add to .mcp.json in your project root:

{
  "mcpServers": {
    "nucleus": {
      "command": "npx",
      "args": ["-y", "nucleus-mcp"]
    }
  }
}

Path Discovery

Nucleus finds your .brain automatically:

1. NUCLEUS_BRAIN_PATH environment variable (explicit)
2. Walk up from CWD looking for .brain/ directory
3. Fall back to $HOME/.nucleus/brain

CLI

Nucleus has a full CLI alongside the MCP tools. Auto-detects TTY (table output) vs pipe (JSON).

# Memory
nucleus engram write my_key "insight here" --context Decision --intensity 7
nucleus engram search "compliance"
nucleus engram query --context Strategy --limit 10

# Tasks
nucleus task list --status READY
nucleus task add "Ship the feature" --priority 1

# Sessions
nucleus session save "Working on auth refactor"
nucleus session resume

# Health
nucleus status --health
nucleus sovereign

# Compliance
nucleus comply --jurisdiction eu-dora
nucleus audit-report --format html -o report.html

# Chat (multi-provider: Gemini, Anthropic, Groq)
nucleus chat

Pipe-friendly:

nucleus engram search "test" | jq '.key'
nucleus task list --format tsv | cut -f1,3

Compliance

One-command configuration for regulatory frameworks:

nucleus comply --jurisdiction eu-dora       # EU DORA
nucleus comply --jurisdiction sg-mas-trm    # Singapore MAS TRM
nucleus comply --jurisdiction us-soc2       # US SOC2

Telemetry

Nucleus collects anonymous, aggregate usage statistics (command name, duration, error type, versions, OS). No engram content, no file paths, no prompts, no API keys, no PII — ever.

nucleus config --no-telemetry
# or: NUCLEUS_ANON_TELEMETRY=false

See TELEMETRY.md for details.

Contributing

• Bug? Open an Issue
• Feature idea? Start a Discussion
• Code? See CONTRIBUTING.md
• Chat? Discord

License

MIT © 2026 | [email protected]