supermemoryai/claude-supermemory

Enable Claude Code to learn in real-time, update it's knowledge, and grow with you, using supermemory.

What it solves

Claude-Supermemory provides persistent memory for AI agents (specifically Claude Code, Codex, and OpenCode) across different sessions and projects. It prevents the AI from forgetting what was worked on in previous interactions, allowing it to maintain context and knowledge of codebase architecture and patterns over time.

How it works

The plugin integrates with the Supermemory service to store and retrieve information. It uses a "reasoned recall" system where the AI decides if recalling a memory is necessary for the current message before searching. It automatically captures conversations when sessions end and can explicitly save important information via the supermemory-save command. To keep project knowledge shared and organized, it uses container tags based on Git remotes to ensure that team members working on the same repository share the same project memory.

Who it’s for

Developers using Claude Code, Codex, or OpenCode who want their AI coding assistant to remember project-specific decisions, architecture, and past work across sessions.

Highlights

  • Team Memory: Shared project knowledge that is separate from personal memories.
  • Reasoned Recall: Automatically searches for relevant memories only when the AI determines it is actually helpful, reducing API usage.
  • Auto Capture: Automatically saves conversations at the end of a session.
  • Project-level Configuration: Supports per-repository settings, API keys, and custom container tags.

Related

  • Project
    supermemoryai/opencode-supermemory

    A plugin for OpenCode that adds persistent, long-term memory to AI agents, allowing them to remember project details and user preferences across sessions.

  • Project
    thedotmack/claude-mem

    A persistent memory compression system for Claude Code that preserves project context across sessions using semantic summaries and hybrid search.

  • Dispatch
    Recall: Local Project Memory for Claude Code

    Recall is an offline, local-first plugin for Claude Code that captures session history and uses a TF-IDF and TextRank summarizer to create durable project memory without spending model tokens.

  • Project
    raiyanyahya/recall

    A fully-local project memory system for Claude Code and other AI agents that uses a classical Python summarizer to create session digests without spending LLM tokens.

  • Project
    JamesShi96/project-butler

    A persistent memory system for AI coding assistants that uses a structured Markdown-based memory stack to maintain project context, rules, and progress across sessions.