⚡ Internal · Eyes Only

Machine.Machine
Weekly System Report

Every Friday at 22:00 UTC, m2 audits the entire fleet — health, memory, org builder, comms, gaps, and evolution plan. This is the live record.

📊 Latest Week — 2026-03-13

Memory Stack Expansion, Autoheal & Intent Engineering
Overall Readiness
71%
Production grade
Active Agents
9
/ 11 deployed
Memory Vectors
4,600+
Qdrant semantic index
Shipped This Week
16
features / fixes / infra
Subsystem Readiness
Fleet Management 76%
Memory System 74%
Autonomous Org Builder 56%
Communication Protocols 70%
Playbook Adoption 64%
Resource Provisioning 60%
Role / Org Science 54%
Dark Factory Engine 57%
🚀 Shipped
m2-memory-engine extension integrated into OpenClaw + Forgejo upstream-sync workflow (10 openclaw commits)
Memory-engine plugin fix rolled out fleet-wide — all agents now have semantic memory access
GLiNER NER microservice deployed — GPU-backed, multilingual, zero-shot named entity recognition
Memgraph knowledge graph service added to agent.memory.system stack
Enhanced agent-autoheal with LLM failover — baked into m2-desktop image
Two-layer config system: openclaw built at image time, config injected at runtime
+ 10 more
🚫 Blocked
🔴Home Assistant still exited/unhealthy — redirect loop unresolved
🔴nasr-m2o at 260% CPU — likely runaway process, needs investigation
🔴Persistent unhealthy containers: Claude proxy, claude-worker, joinly, qwen3-tts, chatterbox-tts, vllm-docker, muninndb-pilot, spacetimedb, Pinokio
🔴kokoro-tts degraded:unhealthy (kokoro-tts container shows g4sw4g40 degraded)
🔴vLLM Qwen3-14B-AWQ reverted from agent-memory-system — local inference still unstable
🔍 Critical Gaps

nasr-m2o CPU runaway — 260%

nasr-m2o container pegged at 260% CPU (3.9 GiB / 8 GiB RAM). Likely infinite loop or stuck LLM request. Needs restart/investigation.

critical

Container sprawl — 10+ unhealthy services

Claude proxy, claude-worker, joinly, qwen3-tts, chatterbox-tts, vllm-docker, muninndb-pilot, spacetimedb, Pinokio, Home Assistant — all exited:unhealthy. Dead weight consuming Coolify slots.

critical

Memgraph hitting 1 GiB memory limit (65%)

memory-memgraph container using 665 MiB / 1 GiB limit. Will OOM as the knowledge graph grows. Limit needs bumping to 2-4 GiB.

warning

memory-embeddings at 14.18 GiB RAM

BGE embeddings model using 14.18 GiB (11.3% of host). Largest single allocation. Consider quantised model or dedicated GPU inference.

warning

vLLM local inference unstable

Qwen3-14B-AWQ was added then reverted this week. Local LLM inference for memory/reasoning pipeline not yet stable.

warning

⚡ Top Actions This Week

1. Restart nasr-m2o and investigate CPU runaway (260% for extended period)
2. Bump Memgraph memory limit to 2-4 GiB before it OOMs
3. Triage and decommission 10 persistent unhealthy containers
4. Re-attempt vLLM Qwen3 stable deployment — use dedicated service config
5. Deploy org_memory shared Qdrant namespace — Memgraph graph is ready
6. Fix Home Assistant redirect loop or decommission
7. Benchmark Intent-router skill accuracy across common task types

📅 Weekly Report Archive

Every Friday — click to explore · 🗂️ Repo Map →
Latest
Week 11 · 2026-03-13
Memory Stack Expansion, Autoheal & Intent Engineering
71%
16 shipped · 5 blocked
Week 10 · 2026-03-06
Video Calls, Onboarding Engine & Fleet Expansion
68%
12 shipped · 4 blocked
Week 9 · 2026-02-27
Fleet Coherence Sprint
62%
10 shipped · 5 blocked

🗺️ Evolution Roadmap

4 phases to self-evolving production system
Phase 0
Foundation
✓ 7 agents deployed
✓ Voice, memory, tasks
✓ Spawn pipeline
✓ Fleet Playbook v0.2
✓ Resource provisioning
Phase 1
Coherence
→ Playbook fleet-wide
→ Fleet heartbeat bus
→ API keys provisioned
→ Conversation archiving
→ CI/CD fixed
Phase 2
Intelligence
○ Org-level memory
○ Per-user memory
○ Capability registry
○ AIEOS roles
○ ACP wiring
Phase 3
Dark Factory
○ Gap detection agent
○ Workflow synthesis
○ Closed CI/CD loop
○ Auto-governance
○ Cost attribution
⚡ Machine.Machine Internal Report · Generated by m2 (orchestrator) · Every Friday 22:00 UTC Not indexed · Internal only