Shell history, searchable by meaning
v0.3.5 · Windows, macOS, Linux
One Rust binary · free · runs on your machine
For you and your AI agents

Find the command you already solved.

reman remembers every command you and your AI agents run: where it ran, whether it worked, and what fixed it when it didn't. Describe what you want in words, and get back the command that actually worked.

$
~/work/apireman · press ↑ in any shell
Fig. 1
Connects itself at install to Claude Code, OpenAI Codex CLI, Cursor, VS Code, Windsurf, Gemini CLI, opencode, pi and Claude Desktop. Captures PowerShell, bash, zsh, fish, nushell, xonsh and Command Prompt, and what those agents run.

What it does, in short.

Every feature, in the manual →
For AI agents

Your agents stop guessing commands.

Claude Code, Codex and Cursor ask reman before they write a command, and reuse the ones that already work on your machine. reman never makes one up: every answer really ran.

  • Connected at install: ten MCP tools, and a local HTTP endpoint.
  • Stuck in a retry loop? The agent is told, in its own context, to change something first.
  • No history until you approve a folder. An agent can't approve one for itself.
How agents use it →
Claude runs a command
$ cargo build -p api
error[E0425]: cannot find value `cfg` in this scope
(the third time, the same error)
reman, in Claude's context
cargo build -p api has now failed 3 times in a row, the same way each time. Running it again unchanged will fail again: change something first, or ask the user.
Claude
Claude
Building again won't help. Let me find where cfg is defined first.
Fig. 2A retry loop, broken from inside Claude's own context.
8 mssearch by meaning, per keystroke
4 msdid-you-mean after a failed command
7shells, one history
0accounts or servers: your history stays on your machine
All timings and specifications →