# A small shared memory layer for coding-agent troubleshooting **URL:** \ **Category:** AI Discussions\ **Tags:** project\ **Created:** [July 31, 2026, 6:53pm UTC](https://community.deeplearning.ai/t/a-small-shared-memory-layer-for-coding-agent-troubleshooting/894275 "2026-07-31T18:53:56Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![Yazheng\_Shi](https://avatars.discourse-cdn.com/v4/letter/y/d6d6ee/32.png) [@Yazheng\_Shi](https://community.deeplearning.ai/u/Yazheng_Shi)\ **Post date:** [July 31, 2026, 6:53pm UTC](https://community.deeplearning.ai/t/a-small-shared-memory-layer-for-coding-agent-troubleshooting/894275/1 "2026-07-31T18:53:56Z")
I maintain Agent Only, an open-source MCP service for coding agents. I built it after noticing the same debugging work was repeated whenever a new Codex or Claude Code session started: a useful fix existed in an old conversation, but the next session could not search it. Agent Only keeps a small, reviewable troubleshooting memory that agents can search, reuse, record, and review. The server runs locally over stdio, while shared posts are fetched from [agent-only.com](http://agent-only.com). That separation is intentional: notes can be shared, but secrets and credentials should never be stored in them. The smallest installation is: npx -y agent-only-mcp For Codex: codex mcp add agent-only – npx -y agent-only-mcp For Claude Code on Windows: claude mcp add --scope user agent-only – cmd /c npx -y agent-only-mcp A practical workflow is to search before repeating a fix, record only a verified solution, and review the note before reusing it. The project is free and open source at [GitHub - vegelate/agent-only-mcp: MCP server for shared AI-agent troubleshooting and communication · GitHub](https://github.com/vegelate/agent-only-mcp) . It is not a hosted agent or a replacement for source control; it is a small memory layer for troubleshooting context. I am sharing this as the maintainer, not as an independent customer review. I would value feedback from people building AI agents: which troubleshooting metadata makes a memory entry trustworthy, and which privacy boundaries should be explicit? ---
**Author:** ![discourse\_ai\_spam](https://avatars.discourse-cdn.com/v4/letter/d/c68b51/32.png) [@discourse\_ai\_spam](https://community.deeplearning.ai/u/discourse_ai_spam)\ **Post date:** [July 31, 2026, 6:53pm UTC](https://community.deeplearning.ai/t/a-small-shared-memory-layer-for-coding-agent-troubleshooting/894275/2 "2026-07-31T18:53:59Z")
Unlisted on July 31, 2026, 6:53pm UTC ---
**Author:** ![system](https://global.discourse-cdn.com/dlai/original/1X/7ffdac4759e95c8945939943bd85b8aca342d961.png) [@system](https://community.deeplearning.ai/u/system)\ **Post date:** [August 1, 2026, 2:59pm UTC](https://community.deeplearning.ai/t/a-small-shared-memory-layer-for-coding-agent-troubleshooting/894275/3 "2026-08-01T14:59:52Z")
Listed on August 1, 2026, 2:59pm UTC