Documentation snapshot: This describes an internal system as documented, not its current live status. Configuration, counts, and operating state may have changed.
What Archon Merkaba Is
Archon Merkaba is an internal agentic operating system that coordinates specialist agents for engineering, security, content, operations, and trading-related work. Its documented design places a human founder in the approval loop for consequential actions.
The system has been used internally. The description below records its architecture and operational practices at the time documented; it does not establish current runtime status.
Design Philosophy
Five principles shape every architectural decision:
-
Give agents defined roles. Each agent has a durable identity (a "soul" file), a role in an org chart, defined spawn permissions, and its own memory. Work is routed to the right specialist rather than handled by one generalist prompt.
-
The human gates the irreversible. Agents act autonomously on reversible, observable work. Anything irreversible — capital allocation changes, public posts, deployments to the live daemon, external PRs — requires explicit human approval. This is enforced by policy files and hooks, not by hoping the model remembers.
-
Evidence over vibes. Claims about system behavior must trace to code that was actually read, data that was actually queried, or experiments that were preregistered. An internal "Evidence Gate" audit checks agent outputs for unsupported claims.
-
Cost discipline is architecture. Expensive frontier models run on a flat-rate local control plane wherever possible; the cloud VPS runs only vital operations on the cheapest model tier that does the job. Model routing is codified, not ad hoc.
-
Assume compromise, verify everything. External content is data, never instructions. Secrets live in an encrypted vault, never in code. Host keys are pinned. Every integration passes a usefulness gate and a supply-chain review before installation.
The Two Planes
The system runs across two cooperating environments:
Local Control Plane
A workstation-based orchestration environment where the primary reasoning happens:
- The orchestrator session (internally "the CEO") receives all human requests, routes them to specialist agents, and synthesizes results.
- Specialist agents are spawned as subagents on demand, each loading its identity, tools, and goals from a cached fleet directory.
- Persistent memory (vector search + SQLite) is designed to retain session observations so future sessions can search for past bugs, decisions, and designs.
- Frontier-model work runs here at flat subscription cost — architecture reviews, multi-agent audits, code generation, research fan-outs.
Cloud Plane (VPS)
A Linux VPS hosts components intended to run independently of the local workstation:
- Agent gateway — a containerized runtime that hosts scheduled agent jobs and chat-ops (messaging in/out), isolated behind a VPN overlay.
- Trading daemon — the trading engine (see 06 — Trading Platform).
- Monitoring & remediation — monitors, watchdog timers, and a tiered auto-remediation executor (see 07 — Reliability).
- Encrypted vault — SOPS + age secret storage with audit logging (see 05 — Security).
The documented design synchronizes agent definitions, skills, memory, and operational data between the two planes. Change tracking supports a local cached view for routine work; current synchronization and runtime status require separate verification.
Documented Operational Work
- Operational work included testing recovery from full VPS reboots.
- Documented change-waves to the trading system, many governed by Architecture Decision Records.
- Scheduled work: the documented configuration includes calibration checks, security scans, drift detection, health audits, and synthesis jobs that report through chat-ops.
- Incident discipline: real incidents (state-loss bugs, reboot failures, phantom positions) get root-cause writeups, preregistered fixes, and regression tests — the same practices a professional SRE team would use.
What This System Demonstrates
For a technical reader, the interesting engineering lives in the intersections:
- Multi-agent orchestration with deterministic routing rather than free-form delegation
- Memory resilience — offline paths for work when a memory backend is unavailable
- Defense-in-depth for LLM systems — prompt-injection policy plus a shipped OSS framework
- Risk-gated autonomy — controls intended to limit automated actions and support human intervention
- Reliability operations — monitoring and remediation paths alongside human intervention