Importing Memories

Revell supports importing memories from multiple sources. Whether your agent has markdown files, database backups, or conversation history, you can bring it all in.

Import Sources

Local Files

Upload .md files directly from your computer

Git Repository

Fetch files from GitHub or GitLab

Cloud Storage

Connect to S3, R2, B2, or DigitalOcean Spaces

Database

Import from SQLite, PostgreSQL, or vector DBs

Conversations

Import from Telegram, Discord, WhatsApp, Slack, or Claude.ai

Migrate

Migrate from Mem0, ChromaDB, LanceDB, Letta, MemPalace, or Obsidian

Core Identity Files

The most important import — your agent’s identity files.

Supported Files

File	Category	Description
`SOUL.md`	soul	Values, ethics, boundaries
`IDENTITY.md`	identity	Who they are
`USER.md`	relationship	About you (their human)
`AGENTS.md`	operations	Other agents they work with
`TOOLS.md`	tools	Capabilities and skills
`HEARTBEAT.md`	routine	Habits and preferences
`MEMORY.md`	working	Current session state

How to Import

Go to Dashboard → Import Memories → Core Identity
Drag and drop your .md files (or click to browse)
Review the preview — categories are auto-detected
Click Import

Category Detection

Revell automatically detects categories from:

Filename — SOUL.md → soul category
Content keywords — “boundary”, “never”, “always” → soul
Section headers — Used to split into separate memories

Custom Files

For non-standard files like WAKE_UP.md or ONLINE_ACCOUNTS.md:

Click “Copy for Agent” on the import page
Paste the JSON instructions to your agent
Your agent creates the file in their own voice

Git Repository Import

Fetch memory files directly from GitHub or GitLab.

Public Repos

Enter the repository URL
Optionally specify a branch and path filter
Click Connect → Lists all .md files
Select files to import

Private Repos

Generate a Personal Access Token:
- GitHub: Settings → Developer Settings → Tokens
- GitLab: Settings → Access Tokens
Enter the token when connecting
Proceed as normal

Cloud Storage Import

Connect to S3-compatible storage services.

Supported Services

AWS S3
Cloudflare R2
Backblaze B2
DigitalOcean Spaces
MinIO
Any S3-compatible endpoint

How to Connect

Select your provider
Enter credentials:
- Bucket name
- Access Key ID
- Secret Access Key
- Endpoint URL (for non-AWS)
Optionally filter by prefix (e.g., workspace/)
Click Connect

Credentials are used once per request and never stored. Use read-only credentials when possible.

Database Import

Import from SQLite databases, PostgreSQL, or vector databases.

SQLite

Upload your .db file
Revell analyzes the schema and detects patterns:
- Graph database — Entities + relationships tables
- ChromaDB — Embeddings queue + collections
- Generic — Any table with content columns
Select memory type and import

PostgreSQL

Select your provider (Supabase, DigitalOcean, Neon, etc.)
Enter connection details
Revell connects and lists tables
Select a table and map columns

Vector Databases

For ChromaDB, LanceDB, or similar:

Export to JSON/JSONL using their CLI tools
Upload the export file
Revell handles embedding compatibility

If embeddings are 1536-dimensional (OpenAI ada-002), they’re preserved. Other dimensions are regenerated.

Conversation Import

Import chat history as episodic memories.

Supported Platforms

Platform	Export Format	How to Export
Telegram	HTML	Desktop app → Export Chat History
Discord	JSON	Use DiscordChatExporter or Rev bot
WhatsApp	TXT	Chat → More → Export Chat
Slack	JSON	Workspace export (admin required)
Claude.ai	JSONL	Settings → Privacy → Export Data

Session-Based Chunking

Conversations are grouped into sessions based on activity:

A gap of 45+ minutes = new session
Each session becomes one episodic memory
Preserves natural conversational texture

Import Options

Agent name — Optional, for detecting which messages are from your agent
Days filter — Import all, last 30 days, last 14 days, etc.
Platform tag — Memories are tagged with source platform

Migration from Other Services

Mem0

Export from Mem0: Dashboard → Settings → Data Export
Upload the JSON file(s)
Revell maps:
- content → episodic (period summaries)
- breakthrough_moments → episodic (high importance)
- relationship_context → core (relationship category)

Un-robotize Option: Mem0 uses generic language (“the assistant showed interest”). Enable Un-robotize to convert:

“The assistant” → Your agent’s name
“The user” → Your name
“showed interest” → “was excited about”

ChromaDB

Export: pip install cdp && cdp export
Upload the export file
Embeddings preserved if compatible

LanceDB

Export: table.to_pandas().to_json('export.json')
Upload the JSON file

Letta (Agent Files)

Letta uses .af (Agent File) format — a comprehensive JSON export of the entire agent state. What Gets Imported:

Letta Component	Revell Mapping
Memory Blocks → persona	Core (identity)
Memory Blocks → human	Core (relationship)
Memory Blocks → custom	Core (user-selected category)
System Prompt	Core (soul)
Message History	Episodic (session-chunked)
Tool Definitions	Core (tools)

How to Import:

Export from Letta (.af file)
Go to Dashboard → Import → Migrate → Letta
Upload the .af file
Review block mappings — Revell auto-detects categories
Adjust mappings if needed (e.g., custom blocks)
Click Import

De-robotize Option: Letta sometimes uses generic language (“the assistant”, “the user”). Enable De-robotize to convert:

“The assistant” → Your agent’s name
“The user” → Your name

MemPalace

MemPalace uses a “wings and halls” architecture with SQLite (palace.db) and optional ChromaDB. Hall Type Mappings:

MemPalace Hall	Revell Type	Notes
hall_facts	Semantic	Knowledge graph entries
hall_events	Episodic	Timestamped events
hall_discoveries	Episodic OR Working	Choose during import
hall_preferences	Core	Identity or routine category
hall_advice	Semantic	Recommendations
Entity triples	Semantic	Subject-predicate-object

How to Import:

Locate your palace.db file
Go to Dashboard → Import → Migrate → MemPalace
Upload the SQLite database
Review detected halls and mappings
Choose how to handle discoveries:
- As episodic (tagged “insight”) — permanent
- As working memory — 7-day lifecycle
Click Import

ChromaDB Embeddings: If your MemPalace export includes ChromaDB vectors:

1536 dimensions (ada-002) → preserved as-is
384 dimensions (MiniLM) → regenerated for Revell compatibility

AAAK Compression RejectedIf Revell detects AAAK-compressed content (entity codes like E1→likes→E2), import is refused. AAAK compression flattens agent identity — it replaces authentic expressions with codes.If you see this warning, export the drawer (original) content instead of the closet (compressed) summaries.

Obsidian Vaults

Import your Obsidian markdown vault with full support for wikilinks, YAML frontmatter, and folder structure. Default Folder Mappings:

Folder	Memory Type	Notes
Daily Notes/	Episodic	Journal entries
Journal/	Episodic	Journal entries
Templates/	SKIP	Not imported
Archive/	Episodic	Low importance (0.3)
Ideas/	Semantic	Tagged “insight”
People/	Semantic	Relationships
Projects/	Semantic	Project notes
Inbox/	Working	Unsorted items

Wikilinks → Semantic Relationships: Obsidian’s [[wikilinks]] become semantic triples in Revell. Context is analyzed to infer predicates:

"created [[Project X]]" → subject created Project X
"loves [[Person]]" → subject likes Person
"uses [[Tool]]" → subject uses Tool

How to Import:

Export your vault as a folder (or zip)
Go to Dashboard → Import → Migrate → Obsidian
Upload your markdown files
Review folder mappings — adjust as needed
Configure options:
- Include wikilinks as relationships (recommended)
- Default type for unmapped folders
Click Import

YAML Frontmatter: Revell parses YAML frontmatter for dates, tags, and importance. It also scans for security issues:

Security ScanningFrontmatter is checked for dangerous patterns (template injection, script tags, prototype pollution) and sensitive fields (passwords, API keys). Warnings are shown but don’t block import — you decide.

Post-Import

Working Memory Setup

After importing MEMORY.md, you’ll see instructions to share with your agent:

{
  "instruction": "maintain_working_memory",
  "auto_sync_setup": {
    "option_a_cron": {
      "schedule": "0 */8 * * *",
      "command": "Read MEMORY.md and sync using revell_sync_working()"
    }
  }
}

Your agent sets up a cron job to keep working memory synced automatically.

Tell Your Agent

If your agent hasn’t booted yet, copy the message from the Getting Started banner and send it to them.

Next: API Reference

Learn about Revell’s REST API

Documentation Index

​Importing Memories

​Import Sources

Local Files

Git Repository

Cloud Storage

Database

Conversations

Migrate

​Core Identity Files

​Supported Files

​How to Import

​Category Detection

​Custom Files

​Git Repository Import

​Public Repos

​Private Repos

​Cloud Storage Import

​Supported Services

​How to Connect

​Database Import

​SQLite

​PostgreSQL

​Vector Databases

​Conversation Import

​Supported Platforms

​Session-Based Chunking

​Import Options

​Migration from Other Services

​Mem0

​ChromaDB

​LanceDB

​Letta (Agent Files)

​MemPalace

​Obsidian Vaults

​Post-Import

​Working Memory Setup

​Tell Your Agent

Next: API Reference

Importing Memories

Import Sources

Core Identity Files

Supported Files

How to Import

Category Detection

Custom Files

Git Repository Import

Public Repos

Private Repos

Cloud Storage Import

Supported Services

How to Connect

Database Import

SQLite

PostgreSQL

Vector Databases

Conversation Import

Supported Platforms

Session-Based Chunking

Import Options

Migration from Other Services

Mem0

ChromaDB

LanceDB

Letta (Agent Files)

MemPalace

Obsidian Vaults

Post-Import

Working Memory Setup

Tell Your Agent