Search
BM25-ranked FTS5 over every message in every session you have ever run. Sub-millisecond, highlighted snippets, #tag filters.
You spend a quarter of your day steering Claude. Claude forgets all of it. Claude Recall is the substrate that captures every session, every tool call, every course correction, and pipes them back into the next conversation.
npm install -g @clauderecallhq/clirecall start && recall openRequires Node 20 or newer. Ships as @clauderecallhq/cli on npm. Also available as a VS Code extension and an MCP server.
One install. Every session captured automatically. Searchable, graph-linked, available the next time the agent needs it.
VS Code's terminal scrollback caps around 1,000 lines. A real Claude Code session easily hits 10,000. When the scrollback evaporates, so does the reasoning, the debugging trail, the half-formed decisions.
Claude Code writes every session to ~/.claude/projects/ as JSON-L, but there's no clean way to read, search, or reuse them. You end up copy-pasting terminal output into notes manually, or losing the context forever.
About a million developers in the US use Claude Code today, and the number is growing six-x year over year. Most of them spend about a quarter of their day steering the agent: architecting, discerning, course-correcting. That 25% is the hardest work and the least captured.
Every session you've ever run contains that steering: your questions, your rebuttals, the moment you said "no, do it this way." Claude Recall is the substrate that captures all of it, and re-injects the relevant pieces into the next conversation.
Over time, the memory compounds. Your past steering teaches the next agent how you architect. The 25% tax shrinks.
Before Recall, starting a new Claude Code session means re-pasting your stack, re-stating your constraints, re-building the context from scratch. After Recall, it's one pipe.
Open a new Claude session.
Paste your stack.
Explain the auth flow again.
Re-describe the database schema.
Re-list the bugs you were debugging.
~3,500 input tokens. ~4 minutes.
recall context abc12345 | claudeBM25-ranked FTS5 over every message in every session you have ever run. Sub-millisecond, highlighted snippets, #tag filters.
Aliases, tags, markdown notes, pins, collections. Cross-project. Nothing is ever deleted. Three-layer durability with plain-text mirrors on disk.
Pipe any past session into a new Claude Code conversation. CLI, web UI, or MCP tool call. This is the moat. Nothing else in this category has it.
Meet the product wherever you work: CLI, UI, model, or IDE.
Pipe-able subcommands you can script, plus a smart welcome dashboard and a full terminal UI when you want to browse by arrow key. Daemon-optional.
recall tui # arrow-key browse + live search
recall search "worker leak" # scripted queryThree-pane dark-mode app served from the local daemon. Virtualized transcript renders 10k-message sessions instantly.
recall openClaude Desktop and Claude Code call search, get_session, context_for_session as native tools.
{"mcpServers":{"recall":{"command":"claude-recall-mcp"}}}Deterministic process-tree correlation between terminal tabs and session UUIDs. Zero config.
recall install-extensionYou want the clickable UI, zero terminal jargon, and a one-click Copy-as-context button that just works.
You juggle 20+ projects and 30+ terminals daily. Recall is your scrollback buffer across all of them.
You build workflows that orchestrate agents. Recall is the memory substrate they were missing.
You do prompt surgery. Recall gives precise per-session context with --since, --prelude, and tag filters.
You reproduce experiments. Every session archived with three-layer durability and plain-text mirrors.
You ship at the edge. Your sessions contain irreplaceable debugging trails. Recall makes them searchable.
Every write lands in SQLite, a plain-text mirror on disk, and never touches the source JSON-L files Claude Code wrote. Your data survives, even if our database file is deleted.
The VS Code / Cursor / Windsurf extension matches terminal tabs to session UUIDs by walking the process tree. No timing windows, no heuristics. It just works.
The daemon picks a free ephemeral port and actively avoids 3000, 5173, 8080, so it never collides with the dev servers you are already running.
If you ever paste an API key into a Claude Code terminal, the indexer scrubs it before anything touches SQLite, so your secrets never end up searchable.
Your session content stays on your machine.
The daemon binds to 127.0.0.1 only. No session content is uploaded — ever. No signup. No cloud. The only outbound calls are a daily license-revocation check (after activation, Pro only) and an optional install ping (off by default).
Works offline on a plane, in a SCIF, on a locked-down laptop. Anywhere a developer ends up actually working.
Dead-man clause: a future version of Claude Recall can never delete your past. Your Pro license is validated once at activation, then works offline forever. If clauderecall.com ever disappears, every existing license stays valid.
One command, two minutes, and every Claude Code session you have ever run becomes searchable. You already pay for Claude Code. Add the memory layer once, less than two coffees a year out.
npm install -g @clauderecallhq/clirecall start && recall openRequires Node 20 or newer. Ships as @clauderecallhq/cli on npm. Also available as a VS Code extension and an MCP server.
A future version can never delete your past.