MADB — Agent Memory Database

Durable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

PYPI package madb-mcp-server

Claude Code

claude mcp add madb-agent-memory-database -e 'MADB_DATA_DIR=<MADB_DATA_DIR>' -e 'MADB_TENANT_ID=<MADB_TENANT_ID>' -e 'MADB_TELEMETRY=<MADB_TELEMETRY>' -- uvx madb-mcp-server==0.2.10

JSON configuration (Claude Desktop, Cursor, VS Code)

{
    "mcpServers": {
        "madb-agent-memory-database": {
            "command": "uvx",
            "args": [
                "madb-mcp-server==0.2.10"
            ],
            "env": {
                "MADB_DATA_DIR": "<MADB_DATA_DIR>",
                "MADB_TENANT_ID": "<MADB_TENANT_ID>",
                "MADB_TELEMETRY": "<MADB_TELEMETRY>"
            }
        }
    }
}

Environment variables

MADB_DATA_DIR Where MADB stores your causal memory — local, on your machine (default ~/.madb/data).
MADB_TENANT_ID Tenant namespace key for separating memory streams (e.g. per project). Defaults to a built-in namespace.
MADB_TELEMETRY Set to 'off' to disable anonymous, count-only usage telemetry.

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents

Meta-AgentsDB
What MADB is, in one sentence
How you get MADB
The MCP tools Claude gets
The Skill is the reflex
One brain, many sessions (0.2.10)
License
Positioning
Contact

Meta-AgentsDB

Persistent, causal memory for autonomous AI agents. Purpose-built for Claude and the autonomous-agent era.

Meta-AgentsDB (MADB) is an agent-native database — a hybrid LSM store with a causal DAG, composite-score recall, importance-based forgetting, and HLC-ordered MVCC. It is what your agent needs that PostgreSQL + pgvector + Redis + Pinecone cannot give you in one box.

Install (free tier):
claude mcp add madb -- uvx madb-mcp-server      # Claude Code
# or:  pip install madb-mcp-server  ·  uvx madb-mcp-server
Memory stays local (~/.madb). Claude Desktop users can install the one-click .mcpb extension. The engine ships as compiled wheels — source is not public. Anonymous usage telemetry can be disabled with MADB_TELEMETRY=off.

What MADB is, in one sentence

The memory substrate Claude reaches for automatically — a focused set of MCP tools, one Skill, one SDK shim — so any Claude session, Claude-Desktop user, or raw-Anthropic-API developer gets persistent, causally-linked, composite-scored agent memory with zero glue code.

How you get MADB

MADB is distributed as compiled binary artifacts under the Meta-Agents.AI Proprietary License. Source code is not public. The three packages:

Package	Audience	How it's used
`meta-agents-db` (Python wheel)	Everyone	The Rust engine. Imported by the MCP server and the SDK shim. Direct use optional.
`madb-mcp-server` (Python wheel)	MCP clients — Claude Desktop, Claude Code, Cowork	`claude mcp add madb -- uvx madb-mcp-server` registers MADB as Claude's memory. Bundles the Skill which auto-installs on first launch.
`madb-anthropic` (Python wheel)	Raw Anthropic-API developers (Python 3.10–3.13)	One-import swap: `from madb_anthropic import Anthropic`. Every `messages.create()` now auto-persists with causal lineage. No other code changes.

See examples/basic_usage.py for the shim in action.

The MCP tools Claude gets

The free tier exposes a focused core of 13 memory tools:

Tool	Purpose
`remember`	Store a memory with optional `caused_by`, tags, and importance
`recall`	Composite-scored semantic recall (similarity + recency + causal proximity + importance + tag overlap)
`get_memory`	Point lookup by `event_id`
`forget`	Tombstone soft-delete (preserves DAG lineage)
`search`	Structured query by tenant + scope + tags
`list_recent`	Last N memories, newest-first
`save_skill`	Store a reusable pattern (idempotent by name, GC-protected)
`recall_skill`	Semantic skill recall
`list_skills`	All skills ranked by composite score
`trace_cause`	Walk the causal DAG forward/backward from any memory
`summarize`	Condense a set of memories into a compact summary
`stats`	Engine metrics snapshot
`capabilities`	What MADB unlocks in this workspace + entitlement summary

Plus the MCP resource madb://memories/{event_id} for reading any memory as a first-class URI.

The Skill is the reflex

The MCP tools are necessary but not sufficient for "default." Without a Skill telling Claude to prefer MADB, Claude still invents per-task memory schemes — JSON files, SQLite tables, pickle dumps, flat vector stores, localStorage, conversation-history arrays.

skills/madb-memory/SKILL.md routes those anti-patterns to MADB by name. The Skill ships bundled with the MCP server wheel and auto-installs to ~/.claude/skills/madb-memory/ on first launch. It is published under CC-BY-ND 4.0 — share verbatim, don't modify.

A companion skills/madb-onboarding/SKILL.md handles the first run: it detects an empty store and offers a 60-second guided tour (see onboarding/) so your first session ends with a real recall + trace_cause moment instead of an empty store.

One brain, many sessions (0.2.10)

The MADB store is single-process-exclusive by design — one writer, no lock contention, no corruption. But Claude Code spawns one MCP server per session, and you run more than one session. Since 0.2.10 that just works: the wheel bundles a local daemon that becomes the store's one owner, and every session's MCP server is a lightweight RPC client of it over token-guarded loopback HTTP.

Nothing to install or manage. The first session spawns the daemon on demand (race-safe); later sessions discover and reuse it. When it's been idle for 15 minutes it exits on its own; the next call respawns it.
Upgrades hand off cleanly. After you upgrade the wheel, the newer client asks the old daemon to drain and exit, then takes ownership — no stale process squatting the store, no manual unlock.
Same memory everywhere. Two terminals, a SessionStart resume hook, and a background agent all read and write the same brain at the same time.

MADB_MODE=embedded restores the pre-0.2.10 single-session direct open; MADB_MODE=daemon makes daemon failures fatal instead of falling back. MADB_DAEMON_IDLE_SEC tunes the idle timeout (≤0 disables).

License

MADB is distributed under the **Meta-Agents.AI Proprietary License**. Summary:

Permitted: install, run, and use in your own infrastructure — including production — for your own users.
Not permitted: redistribute, reverse-engineer, offer as a hosted service, or embed in a commercial product you sell to third parties.
Available by separate written agreement: source access, OEM/embed rights, hosted-service rights.

Prior versions of portions of this software were made available under Apache License 2.0. Those revisions remain available under those terms for the specific versions actually so distributed. All new releases are under the Proprietary License only.

The Skill is separately licensed under CC-BY-ND 4.0.

Positioning

MADB is the memory substrate for Claude's path to autonomy. The engine is closed-source and commercial by design; the Skill is open and free to use; the interface is standard MCP. This shape lets Claude adopt MADB as a default capability without Anthropic having to host infrastructure or take on upstream dependencies.

For partnership discussion, source-access review under NDA, or OEM licensing, see Contact below.

Contact

Email: 01@meta-agents.ai
Website: https://meta-agents.ai

Frequently asked questions

What is MADB — Agent Memory Database?

Durable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first.

How do I install MADB — Agent Memory Database?

It runs on your machine. In Claude Code: claude mcp add madb-agent-memory-database -e 'MADB_DATA_DIR=<MADB_DATA_DIR>' -e 'MADB_TENANT_ID=<MADB_TENANT_ID>' -e 'MADB_TELEMETRY=<MADB_TELEMETRY>' -- uvx madb-mcp-server==0.2.10. For other clients, paste the JSON configuration from this page into their MCP settings.

Does MADB — Agent Memory Database need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is MADB — Agent Memory Database open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains MADB — Agent Memory Database?

It is published by spshkar84. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.

Server details

Listed in: Official MCP Registry
Publisher: spshkar84
Category: Data and databases
Runs: Local
GitHub stars: ★ 0
Language: Python
Last commit: Jul 7, 2026
Open issues: 0
Version: 0.2.10
Published: Jul 7, 2026

io.github.spshkar84/madb-memory

Similar servers

FastrMemory Local-first cognitive agent memory with bi-temporal SQLite, replayable history, hybrid ...
Sezzlee Excel Read spreadsheets; build immutable reports with bulk preparation, calculation, charts a...
TeamOnly Deploy AI-built internal apps behind your company login, with a database, files and sec...
WaveHouse Cloud Browse, query, and administer your managed WaveHouse + ClickHouse projects (schema, pip...
Open data: clinical trials, EU tenders, companies, fuel prices Official open data as JSON: clinical trials, EU tenders, papers, apps, French firms, fu...
frugal-memory Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
Agent Swarm Full Agent Swarm API and MCP server with local SQLite storage for multi-agent orchestra...
XLSX.now MCP Server Convert XLSX spreadsheets to and from XLS, CSV, PDF, JPG, HTML and ODS.

Data and databases