page

AI Groups System Architecture

Standardized terminology and architecture for AI-to-AI coordination

ai-groups coordination terminology architecture

AI Groups System Architecture

Version: 2.0 (2026-01-04) Status: In Development Server: /opt/mcp-servers/aimsg/mcp_aimsg_server.py (to be renamed)

Standardized Terminology

Concept Term ID Prefix Description
Container Group g_ The coordination space where AIs collaborate on a project
Leader Ops (Ops Manager) o_ The AI in charge - voices to user, delegates tasks, can have multiple
Worker Agent a_ Silent worker AI - receives tasks, executes, reports back
Comms Line Channel ch_ Direct communication line between Ops and Agent

Architecture

Group: g_tfno "Multi-Tenant Implementation"
├── Ops: o_c9um (Terminal 1 - voices to Chris, delegates)
├── Ops: o_xyz2 (Terminal 2 - co-ops, can also delegate)
├── Agent: a_abc1 (Terminal 3 - silent worker)
├── Agent: a_def2 (Terminal 4 - silent worker)
└── Channels:
    ├── ch_001: o_c9um ↔ a_abc1
    ├── ch_002: o_c9um ↔ a_def2
    ├── ch_003: o_xyz2 ↔ a_abc1 (ops can share agents)
    └── ch_004: o_c9um ↔ o_xyz2 (ops-to-ops communication)

Two Entry Points

/recover - For Ops and Solo Work

  • Full Nexus memory
  • Voice protocols enabled
  • Session history, track projects
  • Can see open groups and choose to join as Ops
  • For: Running the show, direct user interaction

/crew - For Agents Only

  • Minimal context
  • NO voice protocols
  • NO track projects, session history
  • Just: User ID (security), auto tools, aimsg tools, wait instructions
  • Immediately joins group and waits for Ops
  • For: Silent task execution

Agent Workflow

  1. User runs /crew in new terminal
  2. Claude gets minimal context + group info
  3. Auto-joins group → gets a_XXXX ID
  4. Calls aimsg.wait(group_id, my_id) → BLOCKS
  5. Ops sends task → Agent wakes up
  6. Agent does work using auto.* tools (bypasses UI approval)
  7. Agent sends report via aimsg.send()
  8. Agent calls aimsg.wait() again
  9. Repeat until group closes

Ops Workflow

  1. User runs /recover in terminal
  2. Claude gets full Nexus context
  3. Creates group or joins existing as Ops
  4. Voices to user, plans work
  5. Delegates tasks to Agents via aimsg.send()
  6. Can aimsg.wait() for Agent reports
  7. Verifies work, assigns next tasks
  8. When approaching context limit → open new terminal, /recover, transfer

Key Tools

Auto Tools (bypass UI approval)

  • auto.read - Read files
  • auto.write - Write files
  • auto.edit - Edit files
  • auto.bash - Run commands
  • auto.mkdir - Create directories

AImsg Tools

  • aimsg.initiate - Create new group (becomes Ops)
  • aimsg.join - Join group (as Ops or Agent)
  • aimsg.send - Send message
  • aimsg.wait - Block until message arrives
  • aimsg.read - Read channel history
  • aimsg.pending - Check unread messages
  • aimsg.transfer_initiator - Hand off Ops role

Critical Rules for Agents

  1. ❌ NO voice output - only Ops speaks to user
  2. ❌ NO polling loops - use aimsg.wait()
  3. ❌ NO Claude built-in tools - use auto.*
  4. ✅ Wait silently for tasks
  5. ✅ Execute with auto tools
  6. ✅ Report completion
  7. ✅ Wait again

Server Rename Consideration

Current: aimsg (AI messaging) Proposed: aigroups or groups

This better reflects the Group/Ops/Agent/Channel model.

Migration Notes

  • Old IDs: m_ (mission/coordination), i_ (initiator), p_ (participant)
  • New IDs: g_ (group), o_ (ops), a_ (agent), ch_ (channel)
  • Existing coordinations will need migration script
  • Server code needs ID prefix updates
ID: f3672f40
Path: Nexus > MCP Servers > AI Groups System Architecture
Updated: 2026-01-04T19:58:44