Launching today

RecallLint
Lint your agent's memory before it lies to your agent
2 followers
Lint your agent's memory before it lies to your agent
2 followers
Your coding agent's memory file (CLAUDE.md, AGENTS.md) describes your codebase as it was weeks ago. RecallLint audits it against the current repo: dead paths, dead symbols, stale sources, unsourced claims, duplicates. Free, MIT. Playground + CLI.


Free
Launch Team

AWS Activate CreditsCredits that fuel your startup’s next milestone
Promoted
Hi Product Hunt — I built RecallLint after reading the launch thread of an agent-memory product here last month. One commenter (Ali Naqi Shaheen) wrote: 'A memory learned from a trace 3 weeks ago can be confidently wrong after a refactor, and then every agent sharing it inherits the mistake. Does each memory point back to the trace it came from, and does anything expire it when the code it refers to changes?' Memory storage has plenty of products now. Memory verification had none — so I built the checker. RecallLint reads your CLAUDE.md / AGENTS.md / memory files and checks every claim against your repo as it is today: dead paths, dead symbols, stale sources, unsourced claims, duplicates. It runs locally, it's MIT-licensed, and the demo fixture in the playground shows a real report (10 claims checked · 5 dead · 1 stale · 1 unsourced · 1 duplicate). Honest limits: the unsourced-claim check is a conservative heuristic, and stale/symbol checks run in the CLI (the web playground covers dead paths, unsourced claims, and duplicates). Tell me what your memory files get wrong — I read every comment.
Playground: https://yalakala-naveen.github.i... · Code: https://github.com/Yalakala-Nave...