Remembrall

v1.0.0Knowledge & Memorystable

Persistent knowledge memory layer for AI agents. Hybrid semantic + full-text search with pgvector, code dependency graph with blast-radius impact analysis, and incremental indexing for 7 languages. In-process ONNX embeddings, no external API required

aiai-agentsblast-radiusclaude-codecode-analysis
Share:
18
Stars
0
Downloads
0
Weekly
0/5

What is Remembrall?

Remembrall is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to persistent knowledge memory layer for ai agents. hybrid semantic + full-text search with pgvector, code dependency graph with blast-radius impact analysis, and incremental indexing for 7 languages. in...

Persistent knowledge memory layer for AI agents. Hybrid semantic + full-text search with pgvector, code dependency graph with blast-radius impact analysis, and incremental indexing for 7 languages. In-process ONNX embeddings, no external API required

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Persistent knowledge memory layer for AI agents. Hybrid sema

Use Cases

Persistent knowledge memory for agents
Code dependency analysis and impact
Semantic and full-text search
roboticforce

Maintainer

LicenseMIT License
Languagerust
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx remembrallmcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Remembrall

RemembrallMCP is a persistent knowledge memory layer for AI agents, built in Rust and backed by PostgreSQL with the pgvector extension. It provides hybrid semantic and full-text search over stored memories using in-process ONNX embeddings — no external embedding API required. Beyond memory storage, it includes a code intelligence engine that parses projects in 8 languages into a dependency graph, allowing agents to analyze the blast radius of a proposed change (which symbols depend on a function you're modifying) without scanning the entire codebase at query time. Queries execute in under 10ms regardless of codebase size.

Prerequisites

  • PostgreSQL 16 with the pgvector extension installed
  • Docker and Docker Compose (recommended for easiest setup)
  • Alternatively, Rust 1.94+ to build from source
  • Claude Code, Cursor, or another MCP-compatible client
  • Git to clone the repository
1

Clone the repository

Clone RemembrallMCP from GitHub.

git clone https://github.com/cdnsteve/remembrallmcp.git
cd remembrallmcp
2

Start with Docker Compose (recommended)

Docker Compose handles PostgreSQL 16, pgvector extension setup, and the RemembrallMCP server automatically. This is the quickest path to a working installation.

docker compose up -d
3

Alternative: install prebuilt binary

Download the prebuilt binary for your platform (macOS Apple Silicon or Linux x86_64) from the releases page and initialize the database.

curl -fsSL https://github.com/cdnsteve/remembrallmcp/releases/latest/download/remembrall-linux-x86_64.tar.gz | tar xz
sudo mv remembrall /usr/local/bin/
remembrall init
4

Configure environment variables

Set the PostgreSQL connection string and optional schema name. These can be set in the environment or in ~/.remembrall/config.toml which is auto-created by `remembrall init`.

export REMEMBRALL_DATABASE_URL=postgresql://localhost:5432/remembrall
export REMEMBRALL_SCHEMA=remembrall
5

Register with your MCP client

Add RemembrallMCP to your Claude Code or Cursor configuration to expose the memory and code intelligence tools.

{
  "mcpServers": {
    "remembrall": {
      "command": "remembrall",
      "args": ["serve"],
      "env": {
        "REMEMBRALL_DATABASE_URL": "postgresql://localhost:5432/remembrall"
      }
    }
  }
}
6

Index a codebase for blast-radius analysis

Ask Claude to index your project directory. This parses Python, Java, JavaScript, TypeScript, Rust, Go, Ruby, and Kotlin files into a dependency graph stored in PostgreSQL.

# Via Claude:
# "Index /path/to/my-project into remembrall under the name 'my-project'"

Remembrall Examples

Client configuration

Configure Claude Code to use RemembrallMCP with the PostgreSQL backend. Replace the connection string with your actual database URL.

{
  "mcpServers": {
    "remembrall": {
      "command": "remembrall",
      "args": ["serve"],
      "env": {
        "REMEMBRALL_DATABASE_URL": "postgresql://user:pass@localhost:5432/remembrall",
        "REMEMBRALL_SCHEMA": "remembrall"
      }
    }
  }
}

Prompts to try

Use these prompts in Claude Code after RemembrallMCP is connected to store memories, search knowledge, and analyze code impact.

- "Store this architectural decision: we chose event sourcing over CRUD for the orders service because of audit requirements"
- "Search remembrall for any past decisions about database choice or caching strategy"
- "Index /home/user/projects/api-service into remembrall under the name 'api-service'"
- "What is the blast radius if I modify the AuthMiddleware class? Show me all upstream callers"
- "Look up where the UserRepository class is defined in the indexed codebase"
- "Import all merged PR descriptions from the main branch into remembrall memory"

Troubleshooting Remembrall

pgvector extension not found when running remembrall init

Install the pgvector extension in your PostgreSQL instance: `CREATE EXTENSION IF NOT EXISTS vector;` as a superuser. With Docker Compose this is handled automatically; for manual Postgres installs, follow the pgvector installation guide at https://github.com/pgvector/pgvector.

remembrall_impact returns empty results after indexing

Ensure the indexing completed without errors by checking the output of `remembrall_index`. Some languages require the source tree to be syntactically valid. Re-run the index command and look for parse error warnings.

Docker Compose starts but Claude cannot connect to the MCP server

The remembrall binary inside Docker needs to be accessible to the MCP client. For Docker Compose deployments, expose the server port or mount a shared socket. Alternatively, install the binary locally and point it at the Dockerized PostgreSQL instance using REMEMBRALL_DATABASE_URL.

Frequently Asked Questions about Remembrall

What is Remembrall?

Remembrall is a Model Context Protocol (MCP) server that persistent knowledge memory layer for ai agents. hybrid semantic + full-text search with pgvector, code dependency graph with blast-radius impact analysis, and incremental indexing for 7 languages. in-process onnx embeddings, no external api required It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Remembrall?

Follow the installation instructions on the Remembrall GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Remembrall?

Remembrall works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Remembrall free to use?

Yes, Remembrall is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "remembrallmcp": { "command": "npx", "args": ["-y", "remembrallmcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Remembrall?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides