curl -fsSL https://raw.githubusercontent.com/mayberuk/recall/main/install.sh | sh v1.1.0 · MIT
Every conversation you’ve had with Claude Code or Codex is still on your disk. recall finds the one you’re thinking of in 30 ms — even when you’ve forgotten the words you used.
curl -fsSL https://raw.githubusercontent.com/mayberuk/recall/main/install.sh | sh macOS · Linux · Windows. Checksum verified. Nothing left running.
$ recall findrun from src/payments
| Conversation | Date | Project | Branch | Found |
|---|---|---|---|---|
| 6e2b8d15 | 2026-06-03 | github.com/acme/payments | hotfix/dedupe | 4 matches |
| you | Duplicate charges again. Two merchants hit the same idempotency key and one saw the other’s receipt… | |||
| agent | Scope the idempotency key per merchant, never globally. The key is a string the client chooses, so… | |||
| 3b8a2c94 | 2026-07-21 | github.com/acme/payments | main | 1 match |
| agent | …a retry there needs the idempotency key to be safe, or it must not be retried at all. | |||
The marked one is on hotfix/dedupe — a branch deleted locally months ago. Agents file conversations by folder, so one project scatters across every clone you’ve had. recall recognises a project by its git remote, so all of them are one history.
So it doesn’t make you guess. build finds iosBuild.
retries finds retry. Case never matters.
no turns carry "connection pooling" in github.com/acme/payments connection 14 turns carry it, but not together with the rest pooling no turn carries it; nearby: pool, pooled, pools found elsewhere: 5 hits in 1 other repo github.com/acme/infra 5 hits · 1 session run: recall find 'connection pooling' --all
Empty-handed, it still hands you the closest words in your own history — and points at the project the answer is actually in.
Put any topic on a timeline across your whole history.
“rate limit” · first 12 May · last 21 July · 8 mentions
recall is an MCP server too. Claude Code and Codex query your history mid-task, without you pasting anything.
recall mcp install claude-code“Have we hit this before?” is enough. You never say the word recall.
A few hundred tokens, not a transcript.
Five tools. None can write, delete or alter anything.
Your machine, your files. No account, no upload.
Most search narrows quietly, so “no results” reads as “never happened.” recall ends every answer with what it did and didn’t look at.
It read what you and your agent said to each other — not the output of every command it ran. That is most of what is on disk and almost never what you want. Ask for it and this line says so.
How current the answer is. A conversation from ten minutes ago is already findable. Nothing runs in the background waiting to notice.
What it cost your machine. Seven milliseconds, from cold, reading rather than consulting.
What the answer costs your agent to read. Checking an old decision should be cheaper than redoing it — so every answer prices itself, and you can cap it.
If a limit isn’t printed there, it wasn’t applied.
No index to build, rebuild, or go stale. The conversation is only about 3% of what your agent writes down — the rest is command output.
143 conversations · 1.52 GB. Benchmarks run against a generated history, so they reproduce on your machine — the numbers.