$ loading_
Unifies AI coding transcripts for searchable recall and session memory.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "chat-recall" yet — see the docs or source repo.
Search my past sessions for “database migration” discussions and list the key conclusions.
Returns matching sessions, excerpts, and a concise summary.
Recall the last decision about the authentication refactor and explain why it was chosen.
Summarizes the decision rationale and surrounding context.
Write the findings from this troubleshooting session back into searchable history for later reuse.
Saves the conclusions as searchable history.
Developers switching between Claude Code, Gemini CLI, Codex, and similar tools can search one unified history instead of scattered transcripts. It fits workflows that reuse prior discussions often.
When a team needs to confirm an architecture choice, debugging outcome, or implementation idea, it can trace back through past sessions. This reduces repeated discussion and helps continue earlier decisions.
Useful for writing key conclusions from one-off discussions back into history as reusable long-term memory. It is especially helpful for continuously iterating coding agents.
It is a memory layer for AI coding tools that turns transcripts into one unified, searchable history. It also provides MCP tools for recalling, searching, and writing back decisions.
The description says it indexes transcripts from Claude Code, Gemini CLI, Codex, OpenCode, and Antigravity.
It solves scattered sessions, hard-to-find history, and poor decision reuse across tools. With unified retrieval, agents can quickly recover context and continue prior conclusions.
Persist, search, and reinject context across Claude Code sessions.
Provide persistent memory and hybrid search for AI coding assistants.
Semantically search and expand session history to quickly recall past discussions.
Search past Claude Code chats to recover facts, decisions, and context.
Query all memory stores at once and get a ranked, token-budgeted briefing.
Search and filter Claude Code memory files to retrieve relevant context fast.