{"slug":"mindwright","title":"mindwright","description":"mindwright gives Claude Code persistent, per-agent memory. It captures what happens during a session, distills it into long-term facts via a background consolidation pass, and surfaces only the relevant ones on demand through fully local retrieval (SQLite + on-device embeddings — no API calls). On a fresh install it bootstraps from your existing project transcripts, so recall is useful from day one. Multi-agent aware: each agent keeps its own memory with role-scoped recall.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-12T06:00:00.653Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"Joys-Dawn/toolwright","web_data":{},"github_data":{},"catalog_sources":{"community":[{"name":"mindwright","source":{"ref":"master","sha":"a7a8e85ed719a56725a4abb2a866f92b7a2f4f4f","url":"Joys-Dawn/toolwright","path":"mindwright","source":"git-subdir"},"homepage":"https://joys-dawn.github.io/toolwright/mindwright/","description":"mindwright gives Claude Code persistent, per-agent memory. It captures what happens during a session, distills it into long-term facts via a background consolidation pass, and surfaces only the relevant ones on demand through fully local retrieval (SQLite + on-device embeddings — no API calls). On a fresh install it bootstraps from your existing project transcripts, so recall is useful from day one. Multi-agent aware: each agent keeps its own memory with role-scoped recall."}]}}