C

Cipher

Memory-powered agent framework that provides persistent memory capabilities across conversations and...

103 views
0 installs
Updated Sep 13, 2025
Not audited
Memory-powered agent framework that provides persistent memory capabilities across conversations and sessions using vector databases and embeddings, enabling context retention, reasoning pattern recognition, and shared workspace memory for team collaboration.
  1. Copy the .env Example File (Optional, if not already present)

    • Inside your project directory, run:
      cp .env.example .env
      
    • This creates a .env file with all environment variable placeholders you need.
  2. Locate Your API Keys

  3. (Optional) Set Up Vector Store or Chat History

    • If you wish to use an external vector store (like Qdrant or Milvus) or PostgreSQL for chat history, also obtain corresponding URIs and API keys from your database/vector store service provider.
  4. Open the FastMCP “Install Now” Connection Interface

    • Click the “Install Now” button in your MCP/IDE interface for Byterover Cipher.
  5. Enter Environment Variable Values

    • In the interface, fill in the relevant ENV fields using your keys:

      • For OpenAI:
        OPENAI_API_KEY=sk-...
        
      • For Anthropic:
        ANTHROPIC_API_KEY=sk-ant-...
        
      • For Gemini:
        GEMINI_API_KEY=...
        
      • For Qwen:
        QWEN_API_KEY=...
        
    • If using advanced features, fill in:

      • VECTOR_STORE_TYPE, VECTOR_STORE_URL, and VECTOR_STORE_API_KEY (for Qdrant or Milvus).
      • CIPHER_PG_URL for PostgreSQL chat history.
      • AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_DEFAULT_REGION for AWS Bedrock.
  6. Save and Complete Installation

    • Confirm and save the values in the FastMCP connection interface. The integration will use these environment variables when running Byterover Cipher.

For more details, refer to the official Cipher documentation or LLM provider setup.

Quick Start

View on GitHub

More for Memory Management

View All →

More for Developer Tools

View All →

Similar MCP Servers

M

Memory Plus

Lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions.

Memory Management
M

Memento

Provides persistent memory capabilities through a SQLite-based knowledge graph that stores entities, observations, and relationships with full-text and semantic search using BGE-M3 embeddings for intelligent context retrieval across conversations.

Memory Management
166
0
M

Memoer (Persistent Memory Storage)

Provides persistent memory storage for assistants to create and retrieve memories with filtering options by app name, category, and result limits through a SQLite database with automatic setup.

Memory Management AI and Machine Learning
121
0

Report Issue

Thank you! Your issue report has been submitted successfully.