A Claude Code plugin that gives your AI persistent memory across sessions using Supermemory. Your agent remembers what you worked on - across sessions, across projects.
> /plugin marketplace add supermemoryai/claude-supermemory> /plugin install supermemory@supermemory-plugins
Repo: supermemoryai/claude-supermemory
What's inside
A Claude Code plugin that gives your AI persistent memory across sessions using Supermemory. Your agent remembers what you worked on - across sessions, across projects.
Requires Node.js 18+ on your PATH โ the memory hooks run as Node scripts.
/plugin marketplace add supermemoryai/claude-supermemory
/plugin install supermemory
Already have the old
claude-supermemoryplugin installed? It was renamed tosupermemory, so it won't update in place. Migrate with:/plugin marketplace update supermemory-plugins /plugin install supermemory@supermemory-pluginsThen, only if you still have the old plugin, remove it:
/plugin uninstall claude-supermemory@supermemory-plugins
Set your API key (get one at app.supermemory.ai):
export SUPERMEMORY_CC_API_KEY="sm_..."
Claude Code, Codex, and OpenCode use one container for a repository:
repo_<project-name>__<remote-hash> stores automatic capture and every explicit save.sm_scope metadata keeps personal and project memories filterable inside that container.The hash is derived from the normalized Git remote, so clones share memory while
same-named repositories do not collide. Repositories without a remote fall back to
a local path identity. The agent plugins also read the previous user_project_*,
repo_<project-name>, claudecode_project_*, codex_user_*,
codex_project_*, opencode_user_*, and opencode_project_* containers, so
existing memories remain searchable without a migration. Set
SUPERMEMORY_ISOLATE_WORKTREES=true to use the worktree path instead of the
remote identity.
Explicit repoContainerTag/projectContainerTag overrides remain the canonical
write destination. Older personal/user overrides remain in the legacy read set.
| Command | Description |
|---|---|
/supermemory:index | Index codebase architecture and patterns |
/supermemory:project-config | Configure project-level settings |
/supermemory:logout | Clear saved credentials |
/supermemory:session | Show clickable URL for the current session document in Supermemory |
/supermemory:status | Show authentication status |
Environment
SUPERMEMORY_CC_API_KEY=sm_... # Required
SUPERMEMORY_DEBUG=true # Optional: enable debug logging
Global Settings โ ~/.supermemory-claude/settings.json
{
"maxProfileItems": 5,
"signalExtraction": true,
"signalKeywords": ["remember", "architecture", "decision", "bug", "fix"],
"signalTurnsBefore": 3,
"includeTools": ["Edit", "Write"]
}
| Option | Description |
|---|---|
maxProfileItems | Max memories in context (default: 5) |
recallDirective | Override the built-in reasoned-recall instruction Claude is given |
signalExtraction | Only capture important turns (default: false) |
signalKeywords | Keywords that trigger capture |
signalTurnsBefore | Context turns before signal (default: 3) |
includeTools | Tools to explicitly capture |
Project Config โ .claude/.supermemory-claude/config.json
Per-repo overrides. Run /supermemory:project-config or create manually:
{
"apiKey": "sm_...",
"baseUrl": "https://api.supermemory.ai",
"repoContainerTag": "my-team-project",
"signalExtraction": true
}
| Option | Description |
|---|---|
apiKey | Project-specific API key |
baseUrl | Supermemory API URL |
personalContainerTag | Legacy personal container retained for reads |
repoContainerTag | Override unified project container tag |
For information about how Supermemory collects, uses, and retains data, see the Supermemory Privacy Policy.
MIT
.claude-plugin/
marketplace.json
.github/
workflows/
ci.yml
claude-code-review.yml
claude.yml
.gitignore
biome.json
latest.json
package-lock.json
package.json
plugin/
.claude-plugin/
plugin.json
commands/
index.md
logout.md
project-config.md
session.md
status.md
hooks/
hooks.json
package-lock.json
package.json
scripts/
add-memory.cjs
context-hook.cjs
recall-approve.cjs
recall-hook.cjs
save-project-memory.cjs
search-memory.cjs
status.cjs
summary-hook.cjs
skills/
supermemory-save/
SKILL.md
supermemory-search/
SKILL.md
README.md
scripts/
build.js
src/
add-memory.js
context-hook.js
lib/
auth.js
compress.js
constants.js
container-tag.js
error-helpers.js
format-context.js
git-utils.js
last-session.js
open-url.js
plugin-version.js
project-config.js
result-merge.js
settings.js
stdin.js
supermemory-client.js
transcript-formatter.js
validate.js
version-check.js
recall-approve.js
recall-hook.js
save-project-memory.js
search-memory.js
status.js
summary-hook.js
templates/
auth-error.html
auth-success.html
test/
unit.mjsFAQ
claude-supermemory is a Claude Code plugin with 2 hand-picked skills for agent memory work, indexed on Flowy. Install it with the command on its page. It includes supermemory-save, supermemory-search. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.