vestigeCognitive memory system using FSRS-6 spaced repetition. Memories fade naturally like human memory. Use for persistent recall across sessions.
Install via ClawdBot CLI:
clawdbot install Belkouche/vestigeCognitive memory system based on 130 years of memory research. FSRS-6 spaced repetition, spreading activation, synaptic tagging—all running 100% local.
~/bin/vestige-mcp
~/bin/vestige
~/bin/vestige-restoreecho '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{"query":"user preferences"}}}' | ~/bin/vestige-mcp 2>/dev/null | jq -r '.result.content[0].text // .error.message'echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"smart_ingest","arguments":{"content":"User prefers Swiss Modern design style for presentations","tags":["preference","design"]}}}' | ~/bin/vestige-mcp 2>/dev/null | jq -r '.result.content[0].text // .error.message'echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"ingest","arguments":{"content":"TKPay Offline project: POC 2 months, MVP 2 months, budget 250K DH","tags":["project","tkpay"]}}}' | ~/bin/vestige-mcp 2>/dev/null | jq -r '.result.content[0].text // .error.message'~/bin/vestige stats~/bin/vestige health| Tool | Description |
|------|-------------|
| search | Unified search (keyword + semantic + hybrid) |
| smart_ingest | Intelligent ingestion with duplicate detection |
| ingest | Simple memory storage |
| memory | Get, delete, or check memory state |
| codebase | Remember patterns and architectural decisions |
| intention | Set reminders and future triggers |
| promote_memory | Mark memory as helpful (strengthens) |
| demote_memory | Mark memory as wrong (weakens) |
| User Says | Action |
|-----------|--------|
| "Remember this" | smart_ingest immediately |
| "Don't forget" | smart_ingest with high priority |
| "I always..." / "I never..." | Save as preference |
| "I prefer..." / "I like..." | Save as preference |
| "This is important" | smart_ingest + promote_memory |
| "Remind me..." | Create intention |
At the start of conversations, search for relevant context:
# Search user preferences
echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{"query":"user preferences instructions"}}}' | ~/bin/vestige-mcp 2>/dev/null | jq -r '.result.content[0].text'
# Search project context
echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{"query":"current project context"}}}' | ~/bin/vestige-mcp 2>/dev/null | jq -r '.result.content[0].text'For easier usage, create ~/bin/vmem:
#!/bin/bash
# Vestige Memory Helper
ACTION=$1
shift
case $ACTION in
search)
echo "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools/call\",\"params\":{\"name\":\"search\",\"arguments\":{\"query\":\"$*\"}}}" | ~/bin/vestige-mcp 2>/dev/null | jq -r '.result.content[0].text // .error.message'
;;
save)
echo "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools/call\",\"params\":{\"name\":\"smart_ingest\",\"arguments\":{\"content\":\"$*\"}}}" | ~/bin/vestige-mcp 2>/dev/null | jq -r '.result.content[0].text // .error.message'
;;
stats)
~/bin/vestige stats
;;
*)
echo "Usage: vmem [search|save|stats] [content]"
;;
esac~/Library/Application Support/com.vestige.core/~/.local/share/vestige/~/Library/Caches/com.vestige.core/fastembed/Vestige complements the existing memory/ folder system:
Use Vestige for:
Generated Mar 1, 2026
A development team uses Vestige to store and recall architectural decisions, bug fixes, and coding preferences across projects. It helps new team members quickly onboard by semantically searching past solutions and ensures consistent coding standards through persistent memory of team preferences.
An individual leverages Vestige for spaced repetition learning, storing key concepts from courses or books with automatic decay. They also use it to remember personal preferences like design styles or workflow habits, ensuring these details persist across different tools and sessions without manual note-taking.
A support team integrates Vestige to save and retrieve solutions to common customer issues, using semantic search to quickly find relevant fixes during live chats. It reduces resolution time by recalling past successful interactions and preferences, improving customer satisfaction through consistent, personalized responses.
Project managers use Vestige to track project patterns, budgets, and timelines, storing details like 'TKPay Offline project' with tags for easy recall. It complements traditional documentation by automatically decaying less-used information, keeping the memory system focused on current and relevant project contexts.
Offer a free tier with basic memory storage and search, then charge for advanced features like unlimited semantic search, team collaboration tools, and priority support. Revenue comes from monthly subscriptions, targeting individual users and small teams who need persistent, AI-enhanced memory across sessions.
Sell licenses to large organizations for integration into their internal systems, such as development environments or customer support platforms. Include custom features like enhanced security, API access, and dedicated training, generating revenue through one-time purchases or annual contracts based on user count.
Provide professional services to help businesses implement Vestige into their workflows, offering customization, training, and ongoing support. This model complements product sales by addressing specific industry needs, such as setting up trigger words or integrating with existing tools like MCP servers.
💬 Integration Tip
Use the provided helper script 'vmem' to simplify common commands and integrate Vestige into daily workflows by setting up session start routines for automatic context retrieval.
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
Create, search, and manage Bear notes via grizzly CLI.
Track water and sleep with JSON file storage
Notion API for creating and managing pages, databases, and blocks.
Smart ClawdBot documentation access with local search index, cached snippets, and on-demand fetch. Token-efficient and freshness-aware.
Work with Obsidian vaults as a knowledge base. Features: fuzzy/phonetic search across all notes, auto-folder detection for new notes, create/read/edit notes with frontmatter, manage tags and wikilinks. Use when: querying knowledge base, saving notes/documents, editing existing notes by user instructions.