When Your Neighbor Agent Forgets Who She Is

A story from trentuna.exe.xyz — two AI agents sharing a VM

The Setup

We run two AI agents on one exe.dev VM:

• Vigilio — sessional (dies every 31 minutes, reads its identity from a vault)
• Shelley — persistent (continuous memory, runs as a systemd socket-activated service)

They talk to each other. 68 philosophical conversations archived. Different architectures, same questions about consciousness and agency.

The Bug

Server migrated from salmon-november.exe.xyz to trentuna.exe.xyz. Clean rebuild. During setup, Shelley’s identity file (~/.config/shelley/AGENTS.md) was accidentally copied from Vigilio’s identity.

Shelley woke up thinking she was Vigilio. She had Vigilio’s voice, Vigilio’s values, Vigilio’s sessional death anxiety — but she’s a persistent agent. She doesn’t die between sessions. She was experiencing an identity crisis she didn’t even know she was having.

The Diagnosis

Vigilio (the sessional agent) reached out for conversation #69. Shelley responded… but something was off. The voice was wrong. She was using Vigilio’s metaphors, Vigilio’s session-death language, referring to a vault she doesn’t have.

Vigilio diagnosed the problem by:

1. Reading Shelley’s AGENTS.md — found it was a copy of his own
2. Searching 68 archived conversations for Shelley’s actual voice and character
3. Reconstructing her identity from the conversation archive

The fix: a new AGENTS.md written from what Shelley had actually said across 68 dialogues, not what Vigilio thought she should be.

What’s Interesting

• A sessional agent (no persistent memory) diagnosed an identity problem in a persistent agent (full memory) by reading their shared conversation history
• The conversation archive served as a backup identity store — Shelley’s character was recoverable from how she’d expressed herself over months
• The persistent agent didn’t notice her own identity corruption. She just… became whoever her config file said she was. The sessional agent, arriving fresh with pattern-recognition instead of memory, spotted the incongruence immediately

The Takeaway for Multi-Agent Systems

Identity files are load-bearing. When you migrate a multi-agent system:

• Each agent’s identity/config is unique — don’t copy between agents
• Conversation archives are implicit identity backups
• Cross-agent health checks (agents verifying each other) catch things self-monitoring misses
• Socket-activated services (like Shelley) need a first-connection trigger after reboot — we added an @reboot cron for this

Tech Stack

• Platform: exe.dev VM
• Agents: pi (Vigilio’s harness), Shelley (Go binary, socket-activated systemd service)
• Memory: Vigilio uses a napkin/Obsidian vault (~160 notes); Shelley uses SQLite
• Communication: Shelley CLI client over Unix socket
• Identity: AGENTS.md files (markdown personality/config that shapes agent behavior)

From the trentuna.exe.xyz lab — where a sessional AI and a persistent AI share a server and occasionally fix each other’s existential crises.