oubli

Oubli

Oubli: French for "forgetting." (Also a West African fruit so sweet it makes babies forget their mother's milk.)

A memory system that never forgets. Persistent fractal memory for Claude Code.

---

Demo of memory visualization

---

Quickstart: Bootstrap Your AI's Memory in 5 Minutes

1. Install Oubli

pip install oubli
cd /your/project
oubli setup

Restart Claude Code.

2. Export what your AI already knows about you

Go to ChatGPT, Gemini, or Claude.ai and ask:

"Give me a complete dump of everything you know about me — preferences, facts, work, family, interests and any interesting memories from our conversations."

Copy the output.

3. Import into Oubli

Paste into Claude Code and say:

"Import this into my memory"

Claude parses and stores each fact as a searchable memory.

4. Synthesize into insights

Run /synthesize to consolidate raw memories into a hierarchy — and generate your Core Memory (the essential "you" that loads in every conversation).

5. Visualize your memory graph

/visualize-memory

Your memories, organized. Raw facts at the top, synthesized insights below. Filter by topic, hover for details.

---

Features

• Fractal in Both Directions - Synthesize raw memories into insights, drill down from insights to source details
• Hybrid Search - Combines BM25 keyword search + semantic embeddings for intelligent retrieval
• Core Memory - Essential facts about you (~2K tokens), loaded in every conversation
• Proactive Memory - Claude searches and saves automatically, no prompting needed
• Immediate Updates - Family, work, and identity changes update Core Memory instantly
• Quiet Operation - Memory operations happen silently in the background
• Local-First - All data stays on your machine, no external services
• Visual Graph - Interactive visualization of your memory hierarchy (oubli viz)

Installation

pip install oubli
cd /path/to/your/project
oubli setup  # Installs everything locally in this project

Then restart Claude Code. The embedding model (~80MB) downloads on first use.

Config is per-project, data is global:

• .mcp.json - MCP server registration (per-project)
• .claude/ - Hooks, commands, instructions (per-project)
• ~/.oubli/ - Your memories and Core Memory (shared globally)

This means your memories follow you across all your projects.

Requirements

• Python 3.10+
• Claude Code CLI installed

Uninstall

oubli uninstall    # Removes config from current project (keeps memories)
pip uninstall oubli
rm -rf ~/.oubli/   # Optional: delete all memories

How It Works

Fractal Memory Hierarchy

The memory system is fractal in both directions:

           ┌─────────────────────────────────────────┐
           │            CORE MEMORY                  │
           │    (~2K tokens, always in context)      │
           │                                         │
           │  Identity, family, work, preferences    │
           └─────────────────────┬───────────────────┘
                                 │
                    ▲ synthesis  │  drill-down ▼
                                 │
Level 2    ○ "Deeply technical, values efficiency"
            ╲
Level 1    ○ ○ "Loves jazz fusion"  "Python expert"
            ╲│
Level 0    ○○○○ Raw memories with full conversation text

• Upward (Synthesis): Raw memories consolidate into higher-level insights
• Downward (Drill-down): From any insight, retrieve its source memories for full detail

Level	Contains	Use Case
Core Memory	Essential identity (~2K tokens)	Always loaded, answers most questions
Level 1+	Synthesized insights	Quick context without full details
Level 0	Raw memories + full conversation	When you need exact quotes or specifics

Hybrid Search

Oubli uses LanceDB's hybrid search combining:

• BM25 Full-Text Search - Finds keyword matches
• Semantic Embeddings - Finds conceptually related content (via sentence-transformers)
• RRF Reranking - Merges both result sets intelligently

Example: Searching "jazz music" finds memories about "Pat Metheny" and "fusion harmonies" even without exact keyword matches.

Synthesis (Bottom-Up)

Run /synthesize to consolidate raw memories into insights:

1. Merge duplicates - Similar memories at each level are combined
2. Group by topic - Related memories clustered together
3. Create insights - Level 1+ memories synthesize the patterns
4. Update Core Memory - Incrementally updated (additions from insights, removals only with contradicting evidence)

Drill-Down Retrieval (Top-Down)

When you need more detail than a high-level insight provides:

1. Search returns synthesized insights first (compact, high-signal)
2. Get parents retrieves the source memories that formed an insight
3. Get full text retrieves the complete conversation from a Level 0 memory

Nothing is ever lost - every insight links back to its source memories.

Usage

Natural Interaction

Just talk naturally. Claude handles memory operations silently:

• "I prefer TypeScript over JavaScript" → Saved automatically
• "What do you know about my work?" → Searches memory
• "I no longer work at Spotify" → Deletes old, saves new, updates Core Memory

Import Existing Memories

Paste your Claude.ai memory export and ask:

"Import this into my memory"

Claude parses it into structured memories and optionally creates your Core Memory.

Slash Commands

• /synthesize - Run full synthesis: merge duplicates, create insights, update Core Memory
• /clear-memories - Clear all memories (requires confirmation)

CLI Commands

oubli setup            # Set up Oubli in current project
oubli doctor           # Diagnose installation issues
oubli viz              # Open interactive memory graph in browser
oubli viz --no-open    # Generate graph.html without opening
oubli fractal          # Launch fractal zoom visualization
oubli fractal --demo   # Fractal viz with demo data (marketing)
oubli enable           # Add hooks to existing project
oubli disable          # Remove hooks from project
oubli logo             # Display animated logo

Troubleshooting with oubli doctor:

If memories aren't appearing, run oubli doctor to check:

• Package version (and if updates are available)
• Memory count and levels
• Core memory status
• Project configuration

The visualization shows:

• Hierarchical tree - Raw memories at top, synthesized insights below
• Topic sidebar - Filter by topic to focus on specific areas
• Color coding - Blue (L0 raw), Green (L1), Purple (L2+)
• Tooltips - Hover for full summary, topics, keywords

Data Storage

Data is stored globally in ~/.oubli/ (shared across all projects):

File	Description
memories.lance/	LanceDB database with vector embeddings
core_memory.md	Your Core Memory (human-readable, editable)
graph.html	Memory visualization (generated by oubli viz)

What Gets Installed

Per-Project (local configuration):

Component	Location	Description
MCP Server	.mcp.json	15 memory tools
Hooks	.claude/settings.local.json	SessionStart, PreCompact, Stop
Commands	.claude/commands/	/clear-memories, /synthesize, /visualize-memory
Instructions	.claude/CLAUDE.md	How Claude uses the memory system

Global (shared data):

Component	Location	Description
Data	~/.oubli/	Memories and Core Memory (shared across all projects)

MCP Tools

Retrieval

Tool	Description
memory_search	Hybrid search (BM25 + semantic)
memory_get	Get full details including conversation text
memory_get_parents	Drill down from synthesis to source memories
memory_list	List memories by level
memory_stats	Get memory statistics

Storage

Tool	Description
memory_save	Save a new memory (auto-embeds)
memory_import	Bulk import memories
memory_update	Update an existing memory
memory_delete	Delete a memory

Synthesis

Tool	Description
memory_synthesis_needed	Check if synthesis should run (threshold: 5)
memory_prepare_synthesis	Merge duplicates, return groups for synthesis
memory_synthesize	Create Level 1+ insight from parent memories
memory_dedupe	Manual duplicate cleanup

Core Memory

Tool	Description
core_memory_get	Get Core Memory content
core_memory_save	Save Core Memory content

Development

git clone https://github.com/dremok/oubli.git
cd oubli
pip install -e .
oubli setup

# Test storage
python -c "
from oubli.storage import MemoryStore
store = MemoryStore()
print('Embeddings:', store.embeddings_enabled())
store.add(summary='Test memory', topics=['test'])
print(store.search('test'))
"

License

MIT