/recall list
List recent sessions, then search messages, commands, failures, and skills when you need a specific memory.
session lookup
$ /recall auth 2 matches 2026-03-14 switched JWT to RS256 callback URL had to match env exactly
Session memory for AI coding agents
Your AI should remember things.
agent-recall gives your AI coding agent a filing cabinet instead of a goldfish brain. Save context, distill it, search it later, and restart without replaying your own work back to the model.
circle the useful part, toss the rest
Session memory for AI coding agents.
Save context, distill it, restart with full context.
No more ten-minute re-briefs.
What gets kept?
- decisions
- files touched
- recurring failures
- what to do next
The Index
What's in the box
One command, one memory system. List recent sessions, search remembered work, learn from failures, and restart from saved prompts without dragging a whole framework into the room.
file it where future-you can find it
/recall failures
Track the commands that keep hurting you and surface the fix while the error is still warm.
failure SOP
$ git push origin feature/auth fatal: permission denied recall SOP: switch HTTPS to SSH you hit this three times this month
/recall restart
Load a saved prompt into the current session by default, or add --launch when you want a separate window.
resume work
$ /recall restart --launch 1 opens a separate window without --launch, prompt loads here
Command Surface
One command, practical subcommands.
The homepage mirrors /recall help: plain list and search stay fast, restart loads into the current session unless you ask for a separate window, and shell-history lessons show up through failures and learnings.
/recall help
$ /recall list recent sessions $ /recall list list recent sessions explicitly $ /recall <term> search messages, commands, failures, skills $ /recall '.p8' literal token or filename search $ /recall /.*\.p8/ regex search $ /recall save save current work as a restart prompt $ /recall restart <n|text> load a saved prompt here $ /recall restart --launch 1 open a separate window $ /recall failures failure patterns and approved learnings $ /recall learn review pending learnings $ /recall help show the command help
How It Works
Save. Distill. Restart.
The point is not preserving the transcript. The point is preserving the state of the work without carrying every tangent, typo, and dead-end into the next session.
Save
/recall save captures messages, commands, failures, and current state before the session expires.
step 1
$ /recall save
47 messages
12 commands
2 failures
Distill
Noise comes out. Decisions, files changed, risks, and next steps stay in the briefing.
step 2
kept: branch state, blockers cut: dead-end retries wrote recall-restarts/payroll-fix.prompt
Restart
Load the saved restart prompt and pick up from the middle instead of the beginning. Add --launch only when you want a separate window.
step 3
$ /recall restart 1
branch: feature/payroll-fix
next: verify rounding edge case
Platforms
Works wherever you code
agent-recall is one memory index with a few different doors into it. The shape changes per tool; the session history does not.
Claude Code
- SessionStart hook
- auto-loads recent context
- native slash commands
$ /plugin marketplace add ashrocket/agent-recall
Codex
- AGENTS.md integration
- shared index with Claude Code
- same restart prompts
~/.agent-recall/hooks/scripts/session-start "$PWD"
Gemini CLI
- GEMINI.md integration
- project memory handoff
- same /recall command surface
reads the same recall index
Claude Desktop
- filesystem MCP bridge
- browse saved sessions
- project-level history
point MCP at ~/.claude/projects
The agent-* Family
The toolkit
Three small tools with the same visual language and the same bias: stop dragging context around by hand.
agent-recall
Session memory, failure recall, restart prompts, and searchable work history.
Open the repo ->agent-pb
Prompt builder and context assembly for shaping the right input before the run starts.
Visit agent-pb ->agent-look
Visual capture and browsing help for when the work lives in screenshots, pages, or interfaces.
Visit agent-look ->Install
Put it in the drawer
Primary path is the plugin marketplace. Manual clone stays as the fallback if you want to inspect the wiring yourself.
# Claude Code (plugin) $ /plugin marketplace add ashrocket/agent-recall # Or clone and configure manually $ git clone https://github.com/ashrocket/agent-recall ~/.agent-recall # then copy AGENTS.md or GEMINI.md into your project
The agent-* toolkit
Three small tools, same visual language, same bias: stop dragging context around by hand.