Launching today
Lore
Cited recall from local Codex and Claude Code chats
1 follower
Cited recall from local Codex and Claude Code chats
1 follower
Lore lets a fresh Codex task or Claude Desktop chat find decisions, constraints, and unfinished work in accessible local Codex, Claude Code, and Qwen Code sessions. It returns source references so you can verify the answer. The archive stays on your Windows PC. Free alpha.24; ordinary ChatGPT and Claude cloud chats are outside this release.
Free
Launch Team
Render: Get up to $100K in startup creditsThe fastest way to deploy and scale apps and agents
Promoted
I built Lore because I was tired of being the historian for my coding agents. I'd switch from Codex to Claude and spend the next chat reconstructing decisions we'd already made.
The alpha is deliberately narrow. A fresh Codex task or Claude Desktop chat can ask Lore for evidence from accessible local Codex, Claude Code, and Qwen Code sessions. It returns source references, so you can check what actually happened. The archive stays on your Windows PC.
It does not automatically read ordinary ChatGPT or Claude cloud chats. The Windows binary is unsigned, and a clean-PC install is still unverified. This alpha is free and currently closed source.
If you have old local coding sessions on Windows, I'd love a brutal test: ask a fresh agent about a decision absent from the new chat. Did Lore install, answer correctly, and cite the original message? Tell me where it fails.