Waggle MCP

Project memory for humans and AI agents.
Keep decisions, context, and the reasons behind them across conversations.

Install Waggle · Try the browser workspace · Documentation

Keep the context, not just the conversation

Waggle is an open-source, local-first memory layer for AI agents. It stores project knowledge as a graph: what you decided, why it matters, what it depends on, and what has changed. Your next conversation can pick up from that context instead of starting over.

Use Waggle with your MCP client, inspect and edit memory in Graph Studio, or bring a portable memory graph into the browser workspace.

• Continue across sessions. Recall project decisions, requirements, preferences, and open questions without repeatedly pasting context.
• Understand the reasoning. Explore relationships, supporting evidence, contradictions, and the history behind a decision.
• Keep control of corrections. In the WebMCP workspace, agents propose changes; humans approve the exact content before it becomes authoritative.
• Take memory with you. Export and import .abhi files across supported workflows without tying your graph to one client.
• Start locally. The default SQLite store lives on your machine. Local use does not require a Waggle account or an external database.

Quick Start

The Python package requires Python 3.11+ and pipx. On macOS, you can install pipx with brew install pipx; see the installation guide for client-specific options.

pipx install waggle-mcp
pipx ensurepath

Restart your terminal after the first pipx ensurepath, then run:

waggle-mcp setup --yes
waggle-mcp doctor

Restart your MCP client to load Waggle. Setup detects supported clients and writes their configuration; automatic memory behavior uses the client's installed hooks, skills, or project instructions.

To check continuity, ask your agent to remember a project decision, then open a fresh session in the same project and ask what was decided. Keep the same project identifier across sessions.

Choose your client

For clients that accept an mcpServers configuration:

{
  "mcpServers": {
    "waggle": {
      "command": "waggle-mcp",
      "args": ["serve", "--transport", "stdio"]
    }
  }
}

If the command is not found, run pipx ensurepath and reopen your terminal. Use the troubleshooting guide for installation, startup, and client connection issues.

How memory works

Waggle separates durable project knowledge from the model's context window. An agent retrieves relevant memory when needed and records meaningful outcomes for later conversations.

1. Capture: record decisions, constraints, preferences, and supporting context.
2. Connect: link related memories and preserve contradictions and updates.
3. Recall: retrieve scoped context with evidence and provenance.
4. Continue: use that context in another session or supported client.

The core MCP workflow uses prime_context to load project context, query_graph to retrieve relevant history, and observe_conversation to record durable outcomes. build_context assembles a compact context pack for a specific task. Tool availability alone does not make an agent use memory automatically; its hooks, skills, or instructions must call these tools.

See the tool reference and configuration reference for the full API and retrieval settings.

Graph Studio

Graph Studio makes project memory inspectable and editable. Browse nodes and relationships, add or remove graph content, inspect source evidence, and review how a memory changed over time.

The browser workspace provides focused views for project context, memories, proposals, and activity. Graph Studio provides the graph-level view of that server-backed memory; private browser imports remain in the workspace tab.

Open Graph Studio

WebMCP — memory in your browser

The Waggle workspace lets a human and a compatible browser agent work with the same project memory. Its WebMCP adapter registers page-level Site tools through document.modelContext.registerTool. This is separate from installing Waggle's MCP server or configuring a remote MCP connector.

Connect and use the workspace

1. Open the workspace in ChatGPT's built-in browser using a model and account configuration that supports Site tools.
2. In the address bar, check Site tools → Available site tools and confirm the five Waggle tools are available. Keep this workspace tab open while working with its memory.
3. Explore the sample project or select Load private .abhi to work with your own graph.
4. Ask for a project brief or recall a specific decision. On the hosted workspace, use project_id: waggle-webmcp, including after importing your own graph.
5. To correct a memory, ask the agent to propose a replacement. Review it in Proposals, edit it if needed, and approve the exact value.
6. Ask the agent to apply the approved proposal using only its actual proposal ID. Recall the decision again to confirm the result and inspect its history.

For example:

Call Waggle's get_project_brief with project_id "waggle-webmcp".
Use the returned memories to catch me up on this project.

If Site tools are unavailable, check the browser's permissions and configuration. If the browser blocks an apply call, you can use Apply approved change on the approved proposal and confirm the action yourself. This uses the same approval and freshness checks; it does not bypass browser safeguards.

Browser tools

Corrections you can review

flowchart LR
    A[Agent proposes a correction] --> B[Human reviews and approves]
    B --> C[Waggle checks approval and target version]
    C --> D[Approved value becomes authoritative]
    D --> E[Previous memory stays in history]

Approved content cannot be changed by the applying agent. If the target memory has changed since the proposal was created, the proposal is marked stale instead of overwriting newer information. Application preserves the previous memory and links it to the replacement with an updates edge.

These approval rules govern the WebMCP correction workflow. They are not a claim that every direct graph-editing or local MCP operation requires approval.

Bring your own memory

A .abhi file is Waggle's portable memory graph. The browser importer reads existing memories; it does not ingest a source repository to invent a project brief.

1. Select Load private .abhi in the workspace.
2. Choose an unencrypted schema 2.x file, up to 700 KiB compressed and 4 MiB expanded.
3. Confirm the Private session graph indicator appears. Briefs, recall, proposals, and approvals now use that imported copy.

The import replaces this tab's active workspace; it does not merge with the sample graph, modify your original file, or affect another visitor.

You can also attach the file to a compatible chat and ask:

Use Waggle's load_abhi_for_session tool to load this .abhi file into
project "waggle-webmcp" for this session. Then call get_project_brief.

The agent must be able to read the attachment and provide its bytes as base64. The tool does not accept a local file path or download URL. Use the page's file picker if the chat cannot access the attachment.

See the portable memory format for archive structure and supported operations.

Your data and deployment options