Recallium: From Padawan to Jedi Master
Master your AI's memory in minutes. A hands-on guide to working with shared memory - the prompts you'll use daily, power-user workflows, five rules, and quick fixes.
Try right now
Get value in 60 seconds. Copy-paste these prompts into your AI agent.
recallium→ Loads your full project context
"Remember we chose Postgres because..."→ Stores a decision
"Scan this codebase, document each component, design, and flows in my memories"→ Stores a series of memories for later
"What did we decide about the database?"→ Retrieves it instantly
Command cheat sheet
The prompts that cover most of daily use. Hover a row and hit copy.
recallium"Remember we chose X because Y""Search my memories for auth flow""Search my documents for the API spec""Where did we leave off?""What bugs keep recurring?""Help me think through X vs Y""Create a task: migrate endpoints""Summarize what we did today and save it"What you'll actually do every day
The 5 things you'll use every day. Say these to your agent in plain language.
Store Decisions & Code
You
"Remember this JWT implementation. Access tokens expire in 15 minutes, refresh tokens in 7 days, stored in HTTP-only cookies."
AI
✓ Stored with type: code-snippet Files: src/auth/jwt.ts Tags: authentication, jwt, security
Recall Past Decisions
You
"What did we decide about database choice?"
AI
We chose MongoDB for user preferences because: - Schema flexibility for custom fields - Nested documents for preference hierarchies - Team has more MongoDB experience
Check File Context Before Editing
You
"I'm about to edit src/auth/jwt.ts. What should I know?"
AI
Found 3 relevant memories: 1. JWT Refresh Implementation (2 weeks ago) 2. Bug Fix: Race Condition (1 week ago) 3. Security Enhancement (3 days ago) ⚠️ Token reuse detection is sensitive - test thoroughly if modifying refresh flow.
Search All Your Work
You
"Show me everything we've done on authentication"
AI
Found 8 memories: - 3 implementations (JWT, OAuth2, 2FA) - 2 decisions (JWT over sessions, 15min expiry) - 2 bug fixes (race condition, CORS) - 1 performance improvement (45ms → 8ms)
Resume After a Break
You
"Where did we leave off?"
AI
Last session (2 hours ago): - Implemented rate limiting for login endpoint - Created task: "Add integration tests for auth" - Pending: Review PR for token rotation fix Ready to continue?
Power-user workflows
Advanced features for deeper insights.
Pattern Detection
You
"What patterns have emerged in our API error handling?"
AI
Analyzing 23 memories across 4 projects... Common Patterns: 1. Centralized Error Middleware (3 projects) 2. Domain-Specific Exceptions (strong pattern) 3. Circuit Breaker for External APIs (emerging) Recommendation: Standardize on patterns 1+2.
Bug Root Cause Analysis
You
"Why do we keep having authentication bugs?"
AI
Quality Analysis: Root Causes: 1. Race Conditions (3 occurrences) ⚠️ 2. Token Expiry Edge Cases (2 occurrences) 3. CORS Misconfigurations (2 occurrences) Recommendation: Add integration tests for concurrent auth scenarios (40% of bugs).
Structured Thinking
You
"Help me think through migrating from REST to GraphQL"
AI
🤔 Starting structured thinking... Branch 1: Big Bang Migration - Risk: HIGH, Timeline: 3-4 months Branch 2: Gradual Migration (Facade) - Risk: MEDIUM, Timeline: 6-8 months Branch 3: New Features Only - Risk: LOW, Timeline: Ongoing Recommendation: Branch 2 - proves value incrementally, team learns while productive.
Task Tracking with Context
You
"Remind me to add rate limiting. Link to our auth work."
AI
Task created: "Add rate limiting to login" Linked to: - Memory #1234: JWT implementation - Memory #1245: Auth bug fix Full context available when you return!
Multi-tool & multi-project
One memory layer across all your tools and projects.
Research in Claude Desktop, Code in Cursor
Architect researches and documents in Claude Desktop, then switches to Cursor to implement.
You
"Research best practices for rate limiting APIs. Save your findings to my memories."
Claude
✓ Stored research on rate limiting: - Token bucket vs sliding window algorithms - Redis-based distributed rate limiting - Recommended: 100 req/min for auth endpoints
You
"What did we research about rate limiting?"
Cursor
Found your research from Claude Desktop: - Token bucket recommended for API rate limiting - Use Redis for distributed systems - 100 req/min for auth, 1000 req/min for general Ready to implement based on these findings?
Import Patterns from Another Project
Reuse proven patterns across your codebase.
You
"In the payment-service project, how did we implement error handling middleware? I want to use the same pattern here."
AI
Found error handling pattern from payment-service: 1. Centralized ErrorMiddleware class 2. Custom exceptions: ValidationError, AuthError, NotFoundError 3. Each maps to HTTP status + error code 4. Correlation ID logging for tracing Files: src/middleware/errorHandler.ts Want me to adapt this pattern for your current project?
Cross-Project Insights
You
"What authentication patterns work best across all my projects?"
AI
Analyzing 5 projects... Strongest patterns: 1. JWT + refresh rotation (4 projects, 0 issues) 2. Redis session store (3 projects, stable) 3. RBAC middleware (2 projects, scaling well) Avoid: Cookie-only auth caused CORS issues in 2 projects.
Unified Context Across IDEs
You
"What did I work on yesterday? I used VS Code in the morning and Cursor in the afternoon."
AI
Yesterday's work (both IDEs): Morning (VS Code): - Fixed auth middleware bug - Added rate limiting research Afternoon (Cursor): - Implemented rate limiter based on research - Created task: "Add rate limit tests" All context unified regardless of which tool you used.
Upgrades, backup & migration
Stay current, protect your memories, and move between machines seamlessly.
How to Upgrade
Upgrading is simple - just run the start script again:
# Linux/macOS ./start-recallium.sh # Windows start-recallium.bat
The script automatically pulls the latest version and restarts with your existing data intact.
Why Upgrade Often?
🚀 New Features
We ship improvements weekly - new memory types, better search, UI enhancements, and integrations with the latest AI tools.
🔒 Security Patches
Stay protected with the latest security updates. We patch vulnerabilities as soon as they're discovered.
⚡ Performance
Each release includes optimizations - faster search, reduced memory usage, and improved embedding performance.
🐛 Bug Fixes
We continuously fix issues reported by the community. Upgrading ensures you have the most stable experience.
Tip: Check the changelogto see what's new in each release.
Before updating to a new version, export your data. This ensures you can restore if anything goes wrong.
What Gets Exported
Recallium exports a complete snapshot of your data:
| Data | Details |
|---|---|
| Memories | All content, tags, types, and metadata |
| Embeddings | Pre-computed vectors (no re-processing needed on import) |
| Documents | Uploaded PDFs, text files, and their chunks |
| Document Files | Original uploaded files preserved in ZIP |
| Projects | Project definitions and settings |
| Sessions | Session history and thinking sequences |
Quick Export (Command Line)
The fastest way to backup - use the script in your install folder:
# Linux/macOS ./download-memories.sh # Windows download-memories.bat # Creates: recallium-export-20260403-143052.zip
Export via Web UI
- Open Data Management in the Recallium UI
- Select scope: All Projects or a specific project
- Optional: Set date range to export only recent memories
- Click Preview to see what will be exported
- Click Export to download the ZIP file
Import & Migration
Migrating to a New Machine
Move your complete memory system to a new computer or server.
./download-memories.sh # Copy the ZIP file to your new machine
# Install Recallium first, then: # Open Data Management → Import tab # Select your ZIP file # Choose "Merge" mode # Click Import
Import Modes
| Mode | Use When |
|---|---|
Merge | Add to existing data (recommended) |
Replace | Clear all data first, then import |
Fresh | Empty database only |
Project Mapping
When importing, you can map source projects to different destinations:
- Create new - Creates project with same name
- Merge into existing - Adds memories to an existing project
Useful for consolidating projects or renaming during migration.
API Export (Advanced)
# Export all data curl -o "backup.zip" http://localhost:8001/api/data/export # Export specific project curl -o "project.zip" "http://localhost:8001/api/data/export?project_id=5" # Preview without downloading curl http://localhost:8001/api/data/export/preview
Build the habit
Recallium's value compounds over time. Build these rituals.
recallium"Save what we just did: [describe changes]""Summarize what we accomplished and save it""Where did we leave off?""What context do we have for [filename]?"Five rules for effective memory
Your AI will find past implementations, warnings, and decisions you've forgotten.
Don't save after every line. One comprehensive memory beats ten fragments.
Future you needs the reasoning, not just the decision.
Makes memories searchable by file - critical for the "before editing" workflow.
If you solved something hard, save it. Your AI can't remember what you don't tell it.
Quick fixes
Tap a question to expand.
"AI isn't remembering things"
"Save this""Remember this JWT implementation with refresh token rotation"Look for the AI's confirmation: "✓ Stored with type: ..."
"Search returns nothing"
"getUserByIdAndValidateToken""Search my memories for user authentication"Semantic search finds related concepts - use natural language.
"Found wrong context"
"Find my work""Find my authentication work in the payment-service project"Include project name and topic for precise results.
"Too many search results"
"Show me everything""Find recent authentication decisions in src/auth/"Use filters: recent_only, memory_type, file_path.
Ready to put it to work?
Start with the 60-second quick win, then build the daily habits. Your AI gets smarter with every session.