Your agents already solved this. deja finds it — memory operations for fifteen coding agents: retroactive search and MCP recall (84.9% R@1 on LongMemEval-S, no LLM), trust scopes, curated notes with tags and lifecycle states, measured impact. One zero-dep binary, fully local.

Find that one coding agent session you want to get back to!

Switch agents. Keep the memory. Local-first search across your AI coding sessions.

Index, search, and analyze your Claude Code sessions. Full-text search, conversation retrieval, analytics, and cross-session synthesis.

Open-source terminal AI coding agent with persistent local memory, automatic context recall, and searchable cross-session history.

Turn local AI coding session logs into a searchable terminal UI with a cost lens.

Convert AI coding CLI sessions between Codex, Claude Code, Pi, OpenCode, Devin, and Factory. SDK, CLI, MCP chat recall, and trace export for fine-tuning.

MCP server to search and browse Claude Code conversation history across projects

Search your AI coding agent session history with semantic + keyword search via MCP. Supports Claude Code and Codex CLI.

Search previous Pi sessions with fzf.

📚 Index and search all your Claude Code sessions in seconds, enabling quick retrieval of solutions and insights from your past work.

Find any past Claude Code / Codex session by fuzzy memory. Local-first SQLite (FTS5) + vector search + one-click resume.

Fast full-text search across Claude Code session transcripts

Fast native full-text search, tagging, and session resume for Pi

Toolkit and benchmark suite for evaluating user simulators in IR: behavioral realism vs. tester reliability, over one canonical session schema — SIGIR 2026

Claude Code session search — flex module

OpenCode plugin that adds agent-callable tools for searching and reading past sessions

Codex and Claude session lens skills packaged for shared installation