MCP SERVER • RUST • MEMORY

Octobrain

Name: Octobrain
Brand: Muvon

Persistent Memory • Knowledge Base • MCP Server

Give your AI assistant persistent memory that survives across sessions. Store, retrieve, and relate contextual information with semantic search, temporal decay, and Git-aware project context. Your AI finally remembers.

brew install muvon/tap/octobrain

GitHub

⭐ 9

Learn More

Hybrid BM25 + Vector Search· Temporal Decay· Git Integration· Apache 2.0

13 Memory Types

7 MCP Tools

BM25+ Hybrid Search

∞ Session Memory

Key Features

💾

Persistent Semantic Memory

LLMs don't actually remember — they re-read every message from scratch and drop context when the window fills. Octobrain stores memories externally with vector embeddings and hybrid BM25 + vector RRF fusion, so your AI retains critical context across sessions, not just within them.

📚

Knowledge Base Indexing

Index web pages and documents into a persistent knowledge base. Chunked storage with semantic search means your AI assistant can reference documentation, articles, and specs it has read before — without re-fetching or re-processing.

🔗

Auto-Linking & Memory Graph

Memories automatically connect to related memories via semantic similarity. Build explicit relationships (depends_on, related_to). Ebbinghaus forgetting curve manages importance decay — frequently accessed memories stay relevant, stale ones fade naturally.

Why Octobrain?

AI forgets everything between sessions

✓

Persistent vector storage means memories survive across conversations. Context that matters is always available — not re-explained every time.

Context windows drop critical information silently

✓

When conversations exceed token limits, earlier exchanges are erased without discrimination. Octobrain stores important context externally where it cannot be lost.

No memory prioritization — trivial and critical treated equally

✓

Temporal decay with Ebbinghaus forgetting curve manages importance automatically. Frequently accessed memories strengthen; stale ones fade. You control importance scores.

MCP Tools

Available via Model Context Protocol for AI assistants

memorize Store memories with title, content, type, tags, and importance

remember Semantic search with multi-query support and filtering

forget Remove memories by ID or query match

relate Create explicit relationships between memories

auto_link Discover and connect semantically similar memories

memory_graph Explore memory connections with multi-hop traversal

knowledge_search Search indexed web content and documents

When to Use Octobrain

Cross-Session Context

Your AI assistant remembers decisions, patterns, and preferences from previous sessions. No more repeating "we use PostgreSQL, not MySQL" every conversation.

Project-Aware Memory

Git integration ties memories to specific repositories. Switch projects and your AI loads the right context automatically — architecture decisions, coding patterns, known issues.

Team Knowledge Persistence

Store architectural decisions, bug fix histories, and deployment procedures. New team members get AI that already knows your project's context and conventions.

Research & Documentation

Index API docs, design specs, and competitor analysis. Your AI references previously read material without re-fetching — instant recall of anything it has processed.