# ESAA-Conversational: An Event-Sourced Memory Layer for Continuity, Handoff, and Curation Across Heterogeneous LLM Coding Agents

arXiv: https://arxiv.org/abs/2606.23752 · HTML: https://mlsanity.com/paper/2606.23752/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 4 of its 15 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 4 of 4)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [ESAA: Event Sourcing for Autonomous Agents in LLM-Based Software Engineering](https://mlsanity.com/paper/2602.23193/) (2026)
- [PARCER as an Operational Contract to Reduce Variance, Cost, and Risk in LLM Systems](https://mlsanity.com/paper/2603.00856/) (2026)
- [ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code](https://mlsanity.com/paper/2603.06365/) (2026)

## Abstract (arXiv)

Software developers increasingly work with multiple LLM coding agents, switching among tools such as Codex, Grok, Claude Code, and other assistants as context windows fill, sessions end, or a particular agent becomes better suited to a subtask. Each agent, however, persists its conversation in a private and vendor-specific log. The result is conversational state drift: goals, decisions, open tasks, and rationales established with one agent are not reliably available when another agent takes over. This paper presents ESAA-Conversational, a domain specialization of Event-Sourcing Agent Architecture (ESAA)~citeesaa for shared conversational memory across heterogeneous agents. The method treats the visible conversation as a local event store: hooks and watchers capture visible turns, normalize them into an append-only textttactivity.jsonl, and deterministically project read models such as texttthandoff.md, textttstate.md, textttdecisions.md, and texttttasks.json. Mechanical capture does not require LLM inference; agents use judgment only for explicit curation, recording durable decisions and conversational tasks through domain commands. The public v1.1.0 release implements a PowerShell CLI with textttinit, textttenable-hooks, textttsync, textttproject, textttverify, textttcontext, textttdecide, and texttttask; includes textttworkspaceroot isolation and a write-path lockfile; and is distributed as a greenfield package with an empty public log. A self-referential case study with 570 development-lab events shows that heterogeneous agents can collaborate through a shared log without a direct agent-to-agent channel, while the public distribution preserves privacy by excluding the private conversational history.