RemembrallMCP

RemembrallMCP

Whole-codebase knowledge for AI coding agents. A field-aware code graph plus persistent memory, built on Rust, Postgres + pgvector, and exposed over MCP.

The problem: AI coding agents see a few pages out of the book each session. They grep, read, and re-derive how the codebase fits together from scratch - no map of what calls what, no way to know what breaks when something changes, and no memory of decisions made in past sessions.

The solution: RemembrallMCP gives the agent the whole codebase - a field-aware dependency graph (functions, classes, methods, fields, and the references between them) across 9 languages, plus persistent memory that survives between sessions.

1. Field-Aware Code Graph - A live map of your codebase built with tree-sitter. Functions, classes, methods, and data fields, plus call, import, defines, inherits, and field-reference relationships across 9 languages. Ask "what breaks if I change this?" - down to a single struct field - and get an answer in milliseconds, before the agent touches anything.

2. Persistent Memory - Decisions, patterns, and organizational knowledge that survive between sessions. Hybrid semantic + full-text search finds relevant context instantly.

remembrall_recall("authentication middleware patterns")
-> 3 relevant memories from past sessions

remembrall_index("/path/to/project", "myapp")
-> Builds dependency graph: 847 symbols, 1,203 relationships

remembrall_impact("AuthMiddleware", direction="upstream")
-> 12 files depend on AuthMiddleware (with confidence scores)

remembrall_impact("amount", direction="upstream")
-> methods that read self.amount, across the whole codebase

remembrall_store("Switched from JWT to session tokens because...")
-> Decision stored for future sessions

Why the code graph matters

Without RemembrallMCP, agents explore your codebase from scratch every session. Claude Code spawns Explore agents, Codex reads dozens of files, Cursor greps through directories - all burning tokens and time just to understand what calls what. A single "find all callers of this function" task can cost thousands of tokens across multiple tool calls.

With RemembrallMCP, that same query is a single remembrall_impact call that returns in <1ms with zero exploration tokens. The dependency graph is already built and waiting.

The savings scale with codebase size. On a small project, an agent can grep and read its way through. On a 500-file monorepo, that exploration becomes the bottleneck - agents hit context limits, spawn multiple sub-agents, or miss cross-module dependencies entirely. RemembrallMCP's graph queries stay under 10ms regardless of project size because the structure is pre-indexed in Postgres, not discovered at runtime.

This is the difference between an agent that reads a few pages out of the book every time and one that already holds the whole codebase.

Benchmarks

RemembrallMCP is currently benchmarked on two surfaces:

• Agent productivity on code tasks - Tested on pallets/click v8.1.7 (594 symbols, 1,589 relationships). Five identical coding tasks run with and without RemembrallMCP. Full report.
• Memory recall quality - Local recall harness run against 31 ground-truth queries covering search quality, filtering, edge cases, ranking, and latency.

The savings compound on larger codebases. Click is ~90 files - on a 500+ file monorepo, agents without RemembrallMCP need proportionally more exploration calls, while graph queries stay under 10ms regardless of size.

Run the benchmarks yourself: see benchmarks/ for the harness and task definitions.

For the broader benchmark strategy across memory retrieval, long-horizon memory, code graph correctness, and agent productivity, see docs/benchmark-roadmap.md.

Requirements

• Docker (for the easiest setup) or PostgreSQL 16 with pgvector
• For GitHub ingestion: GitHub CLI (gh) installed and authenticated

Quick Start

Option 1: Docker Compose (easiest)

git clone https://github.com/roboticforce/remembrallmcp.git
cd remembrallmcp

# Start Postgres, initialize the schema, download the embedding model,
# and run the MCP server. The remembrall container stays up after setup.
docker compose up -d

# Verify it's running (database connected, schema ready)
docker compose exec remembrall remembrall status

That's it. Postgres with pgvector, the schema, and the embedding model are all set up automatically. The database and model cache persist across restarts.

The remembrall container runs remembrall init (idempotent setup) followed by remembrall serve on startup, so it stays running and docker compose exec works for status, doctor, and other commands.

To connect an MCP client (Claude Code, Cursor, Codex) to the server, see Connect to your MCP client below.

Option 2: Download prebuilt binary

# macOS (Apple Silicon)
curl -fsSL https://github.com/roboticforce/remembrallmcp/releases/latest/download/remembrall-aarch64-apple-darwin.tar.gz | tar xz
sudo mv remembrall /usr/local/bin/

# Linux (x86_64)
curl -fsSL https://github.com/roboticforce/remembrallmcp/releases/latest/download/remembrall-x86_64-unknown-linux-gnu.tar.gz | tar xz
sudo mv remembrall /usr/local/bin/

# Initialize (sets up Postgres via Docker, creates schema, downloads model)
remembrall init

Option 3: Build from source (requires Rust 1.94+)

cargo build -p remembrall-server --release
# Binary is at target/release/remembrall

remembrall init

Connect to your MCP client

Codex

Codex uses the same MCP server definition format. Register the server as remembrall and point it at either the installed binary or your local release build.

If remembrall is installed in PATH:

{
  "mcpServers": {
    "remembrall": {
      "command": "remembrall"
    }
  }
}

If running from a local source checkout:

{
  "mcpServers": {
    "remembrall": {
      "command": "/path/to/remembrallmcp/target/release/remembrall",
      "env": {
        "DATABASE_URL": "postgres://postgres:postgres@localhost:5450/remembrall"
      }
    }
  }
}

If using Docker Compose from Codex:

{
  "mcpServers": {
    "remembrall": {
      "command": "docker",
      "args": ["compose", "-f", "/path/to/remembrallmcp/docker-compose.yml", "run", "--rm", "-T", "remembrall"]
    }
  }
}

Restart Codex after adding the server so it reconnects and loads the tools.

Claude Code, Cursor, and other MCP clients

Add to your project's .mcp.json (works with Claude Code, Cursor, and any MCP-compatible client).

If using a prebuilt binary or built from source:

{
  "mcpServers": {
    "remembrall": {
      "command": "remembrall"
    }
  }
}

If using Docker Compose:

{
  "mcpServers": {
    "remembrall": {
      "command": "docker",
      "args": ["compose", "-f", "/path/to/remembrallmcp/docker-compose.yml", "run", "--rm", "-T", "remembrall"]
    }
  }
}

Each invocation starts a fresh container, runs remembrall init (idempotent; its output goes to stderr so it never corrupts the MCP stream), then remembrall serve over stdio. The -T flag is required - it disables TTY allocation so JSON-RPC passes through cleanly. The db service starts automatically via depends_on.

If running from source (not installed to PATH):

{
  "mcpServers": {
    "remembrall": {
      "command": "/path/to/remembrallmcp/target/release/remembrall",
      "env": {
        "DATABASE_URL": "postgres://postgres:postgres@localhost:5450/remembrall"
      }
    }
  }
}

Restart your MCP client. All 9 tools will be available automatically.

Try it

> "Store a memory: We chose Postgres over MongoDB because our query patterns
   are relational. Type: decision, tags: database, architecture"

> "Recall what we know about database decisions"

> "Index this project and show me the impact of changing UserService"

MCP Tools

Memory