Keep one memory across Claude Code, Codex and Cursor when you switch tools
Two founders kept switching coding agents whenever usage limits ran out or a better model came out, and had to re-explain tasks, workflows and past mistakes each time. They built an open-source, cross-harness memory layer the agents share.
Source
shakshukan on Hacker News · 2026-10-21
Written in our own words. Credit to the original author. Link checked 2026-10-22.
What they did
Two founders kept switching coding agents whenever usage limits ran out or a better model came out, and had to re-explain tasks, workflows and past mistakes each time. They built an open-source, cross-harness memory layer the agents share.
Result (as claimed)
Released open source; switching agents no longer means starting from zero.
Tools they used
Cost: Claude Code: from $17/mo; OpenAI Codex: free plan, paid from $8/mo; Cursor: free plan, paid from $8/mo.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude Code, OpenAI Codex, Cursor. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Keep one memory across Claude Code, Codex and Cursor when you switch tools What the original author did: Two founders kept switching coding agents whenever usage limits ran out or a better model came out, and had to re-explain tasks, workflows and past mistakes each time. They built an open-source, cross-harness memory layer the agents share. Reported result (as claimed by the author): Released open source; switching agents no longer means starting from zero. Source: https://news.ycombinator.com/item?id=50182883 Tools they used: Claude Code, OpenAI Codex, Cursor Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Keep one memory across Claude Code, Codex and Cursor when you switch tools What the original author did: Two founders kept switching coding agents whenever usage limits ran out or a better model came out, and had to re-explain tasks, workflows and past mistakes each time. They built an open-source, cross-harness memory layer the agents share. Reported result (as claimed by the author): Released open source; switching agents no longer means starting from zero. Source: https://news.ycombinator.com/item?id=50182883 Tools they used: Claude Code, OpenAI Codex, Cursor Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Keep one memory across Claude Code, Codex and Cursor when you switch tools What the original author did: Two founders kept switching coding agents whenever usage limits ran out or a better model came out, and had to re-explain tasks, workflows and past mistakes each time. They built an open-source, cross-harness memory layer the agents share. Reported result (as claimed by the author): Released open source; switching agents no longer means starting from zero. Source: https://news.ycombinator.com/item?id=50182883 Tools they used: Claude Code, OpenAI Codex, Cursor Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to run multiple coding agents together · How to vibe code an app with Claude Code · How to save, share and resume coding agent sessions · How to use Claude Code and Codex together
Related use cases
Keep all your Claude Code, Codex and Cursor chats searchable in one place
ChatVault collects chats from Claude Code, Codex and Cursor across accounts, lets you search the whole history and keeps local backups.
Carry shared memory across Claude, Codex and Cursor with thred
Shipped thred so Claude, Codex, Cursor and future agents share one MCP memory for decisions, revisions, evidence and unfinished work.
Give Claude Code, Codex and Cursor one shared, self-improving memory
An AI educator connected Claude Code, Codex and Cursor to one memory layer, so a correction made in Cursor carries over to Claude Code and skills built in Codex are available everywhere. The memory updates itself as the agents learn.
Track token spend across Claude Code, Codex and Cursor in one local window
LunoPeak shows every AI coding session in one local window with live sessions, per-session token spend and budget alerts. No account, no cloud and no telemetry.