io.github.eidetic-works/nucleus
io.github.eidetic-works/nucleusSovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents.
Tools · 28
Governance, Hypervisor & security tools for the Nucleus Agent OS. Actions: auto_fix_loop - Auto-fix loop: Verify->Diagnose->Fix->Verify (3 retries). params: {file_path, verification_command} lo…
Feature tracking, proof generation & MCP server mounting. Actions: add - Add a feature. params: {product, name, description, source, version, how_to_test, expected_result, status?, tags…
Session management, events, state & checkpoint tools. Actions: save - Save session for later. params: {context, active_task?, pending_decisions?, breadcrumbs?, next_steps?} resume …
Task management, depth tracking & ADHD context-switch tools. Actions: list - List tasks. params: {status?, priority?, skill?, claimed_by?, required_role?} get_next - Get hig…
Sync, artifact, trigger & deploy management for multi-agent coordination. Actions: identify_agent - Register agent identity. params: {role, provider, session_id} (per ADR-0005 §D1) …
Get the next unread relay message. One call — returns full message body and auto-acks. Long-poll (60s timeout). This is the agent's idle loop. Call it, get a message or None, act or re-call. No separ…
Long-poll subscription that pushes ctx.info() on each new inbox file. Replaces bash polling daemons (watch-relay-*.sh) with server-initiated push. Call once at session start (e.g. via SessionStart ho…
One-shot convenience: resolve canonical inbox + arm long-poll subscription. Per PR #2 (CCR server-side auto-arm) — IDE-agnostic relay-arrival arming. This is the RECOMMENDED entry point for SessionS…
Quick scan for a PENDING task. Returns the task directly if one is available, or None if no task is ready within the timeout. Default timeout is 5s (non-blocking). The agent should NOT loop on this —…
Satellite view, commitments, loops, patterns & metrics. Actions: satellite - Unified satellite view. params: {detail_level?} scan_commitments - Scan artifacts for new commitments archi…
LLM tiers, telemetry, PEFS notifications & protocol tools. Actions: set_llm_tier - Set default LLM tier. params: {tier} get_llm_status - Get LLM tier configuration record_interact…
Orchestration slots, sprints & mission management. Actions: orchestrate - THE GOD COMMAND. params: {slot_id?, model?, alias?, mode?} slot_complete - Mark task complete. params: {slot_…
Infrastructure: file changes, cloud, marketing & strategy tools. Actions: file_changes - Get pending file change events gcloud_status - Check GCloud auth status gcloud_services …
Agent spawning, critic, swarm, memory, ingestion & dashboard tools. Actions: spawn_agent - Spawn Ephemeral Agent. params: {intent, execute_now?, persona?, confirm?}. HITL: requires confirm…
Federation management for multi-brain coordination. Actions: status - Get comprehensive federation status join - Join a federation via seed peer. params: {seed_peer} leave - Leave the fed…
Engrams, health, observability, DSoR & tier system tools. Actions: health - Get system health status version - Get Nucleus version info export_schema - Export MCP…
Relay-substrate facade — post / read / ack / status. Actions: post - Send a relay envelope. params: {to, subject, body, sender?, priority?, in_reply_to?, context?, id?, from_session_…
W5 tier routing — route a prompt to the optimal model tier. Actions: route - Route a prompt to cheapest capable model. params: {prompt, complexity?, context?, estimated_output_tokens?} …
W8 Team-tier tamper-evident audit log (SHA-256 hash chain). Actions: log_event - Append an audit event to the chain. params: {event_type, actor, resource, outcome, metadata?, team…
Hand a coding or review task to a cross-vendor lane — a cheap, non-Claude agent that does the work for you. Use this INSTEAD OF shelling out to any CLI: it picks the vendor, injects the correct per-ve…
Set up an autonomous task-execution loop in a git repo. WHEN TO USE: you have a list of tasks (bugs, features, tests) you want executed automatically without manual prompting — the lane runs watcher/e…
Start autonomous lane daemons (watcher + executor + secretary) in background. WHEN TO USE: after nucleus_lane_init and SPEC.md is written — this launches the loop that autonomously claims and executes…
Stop all running lane daemons. WHEN TO USE: when all tasks are CONFIRMED or you want to pause autonomous execution.
Check lane status: task counts (PENDING/IN_PROGRESS/DONE/CONFIRMED), daemon health, spec verification. WHEN TO USE: after starting a lane to monitor progress, or before starting to check if a lane is …
Report friction/bugs/enhancements to the nucleus team. WHEN TO USE: when the lane misbehaves, a task fails unexpectedly, the SPEC.md format is confusing, or you have an improvement idea. Creates a Git…
Execute a plan file autonomously. WHEN TO USE: you have a plan file (.brain/plans/*.md) you want executed autonomously — parses the plan, creates tasks, starts a mission with budget/time limits. Chain…
Import a plan file as PENDING tasks without starting a mission. WHEN TO USE: you have a plan file (.brain/plans/*.md) you want loaded into the task store so the executor daemon / sprint mission can pi…
List available plan files in .brain/plans with task counts. WHEN TO USE: you want to discover which plan files exist and how many tasks each contains before importing or executing one. Returns: J…
Resources · 19
Live state.json content - subscribable.
brain://state
Recent events - subscribable.
brain://events
Trigger definitions - subscribable.
brain://triggers
Current depth tracking state - subscribable. Shows where you are in the conversation tree.
brain://depth
Full context for cold start - auto-visible in sidebar. Click this first in any new session.
brain://context
Change ledger — poll THIS to detect staleness across all brain:// resources.
brain://changes
Full list of recent DecisionMade traces - subscribable.
brain://traces
Three Frontiers health — GROUND/ALIGN/COMPOUND status at a glance.
brain://health
Current compounding cycle — weekly progress tracking. Subscribable.
brain://cycle
Session continuity — recent sessions and today's focus. Subscribable.
brain://arc
Delta archive summary (7-day window) — pattern extraction from COMPOUND frontier.
brain://deltas
Training pipeline readiness — SFT/DPO counts and retrain signal.
brain://training
Three Frontiers health dashboard — GROUND/ALIGN/COMPOUND in one view.
brain://frontiers
Business function metrics — growth gates and dogfood health.
brain://growth
Claim Survival Rate — the compounding trust scalar.
brain://flywheel/csr
Flywheel dashboard JSON — CSR + tickets + curriculum + recent claims.
brain://flywheel/dashboard
The $5T flywheel thesis — why the compound loop has to exist.
brain://flywheel/thesis
Flywheel mentor — open challenges + things NOT to do.
brain://flywheel/mentor
Current ISO-week report — flywheel activity over the last 7 days.
brain://flywheel/week
Prompts · 8
Activate Synthesizer agent to orchestrate the current sprint.
Initialize a new sprint with the given goal.
Get instant context when starting a new session. Call this first in any new conversation.
COMPOUND frontier context — Delta patterns, recurring negatives, learning opportunities.
ALIGN frontier context — human corrections and what the system should learn.
Full-organism weekly synthesis — all three frontiers + business metrics.
FLYWHEEL — how's the compounding loop doing right now? Returns a one-screen summary of CSR, open tickets, and curriculum depth. Use this at the top of any session that touches driver work.
FLYWHEEL — brief me on this week's activity. Returns the current ISO-week report verbatim. Use when you want the narrative, not the dashboard numbers.
Similar MCP servers embedding-nearest
How to use
Add to your Claude Desktop / Cursor / Cline MCP config:
{
"mcpServers": {
"io.github.eidetic-works/nucleus": {
"url": "https://relay.nucleusos.dev/mcp",
"transport": "streamable-http"
}
}
}