
Description
Overrides the auto-detected project scope to read and write memories under a different project ID, or enables global search to access all memories across all users and projects. Use when working across multiple projects, accessing memories from another repo, enabling team-wide memory access, or when auto-detection resolves to the wrong project.
SKILL.md
Mem0 Switch Project
Override the automatic project_id detection for the current directory, or enable global search mode.
Usage
/mem0:switch-project <project-name>— switch to a specific project scope/mem0:switch-project --global— enable global search (all memories, all users, all projects)/mem0:switch-project --no-global— disable global search and return to per-project scoping
Execution
If --global flag is provided:
- Set
global_search: truein~/.mem0/settings.jsonusing the Bash tool:python3 -c " import json, os settings_file = os.path.expanduser('~/.mem0/settings.json') settings = {} if os.path.isfile(settings_file): with open(settings_file) as f: settings = json.load(f) settings['global_search'] = True with open(settings_file, 'w') as f: json.dump(settings, f, indent=2) print('Global search enabled') " - Print:
Global search enabled. Searches now return all memories across all users and projects. Writes still use the current user_id and app_id. Restart the session for the change to take effect.
If --no-global flag is provided:
- Set
global_search: falsein~/.mem0/settings.jsonusing the Bash tool:python3 -c " import json, os settings_file = os.path.expanduser('~/.mem0/settings.json') settings = {} if os.path.isfile(settings_file): with open(settings_file) as f: settings = json.load(f) settings['global_search'] = False with open(settings_file, 'w') as f: json.dump(settings, f, indent=2) print('Global search disabled') " - Print:
Global search disabled. Searches now return only memories scoped to the current project. Restart the session for the change to take effect.
If a project name is provided (no flags):
- If no project name was given, ask: "What project_id should this directory use?"
- Write the mapping to
~/.mem0/project_map.jsonusing the Bash tool:python3 -c " import json, os map_file = os.path.expanduser('~/.mem0/project_map.json') mapping = {} if os.path.isfile(map_file): with open(map_file) as f: mapping = json.load(f) mapping[os.getcwd()] = '<PROJECT_NAME>' os.makedirs(os.path.dirname(map_file), exist_ok=True) with open(map_file, 'w') as f: json.dump(mapping, f, indent=2) print(f'Mapped {os.getcwd()} -> <PROJECT_NAME>') "
(Replace<PROJECT_NAME>with the user's chosen project name.) - Verify by searching for existing memories:
- Call
search_memorieswithquery="project",filters={"AND": [{"user_id": "<active_user_id>"}, {"app_id": "<PROJECT_NAME>"}]},top_k=1
- Call
- Print:
Switched to project <PROJECT_NAME>. <N> memories found for this project. Note: This override persists across sessions for this directory.
More skills from the mem0 repository
View all 23 skillscontext-loader
load project context from Mem0
Jul 13AgentsContextMemorydream
consolidate and prune stored memories
Jul 13AgentsData CleaningMemoryexport
export project memories to Markdown files
Jul 13BackupMemoryMigrationforget
delete outdated or incorrect memories
Jul 13MaintenanceMemoryPrivacyhealth
diagnose Mem0 connectivity and health
Jul 13DebuggingMemoryMonitoringimport
import project memories from Markdown files
Jul 13MarkdownMemoryMigration
More from Mem0
View publisherlist-projects
list projects with stored memories
mem0
Jul 13AgentsMemorymem0
add persistent memory to AI applications
mem0
Jul 13AgentsAI InfrastructureMemorymem0-cli
manage Mem0 memory via command line
mem0
Jul 13AutomationCLIMemorymem0-integrate
integrate Mem0 into repositories
mem0
Jul 13AgentsAPI DevelopmentMemorymem0-oss-to-platform
migrate Mem0 projects to platform
mem0
Jul 13AgentsMemoryMigrationmem0-test-integration
verify Mem0 integration tests
mem0
Jul 13AgentsMemoryQATesting