monet

mcp
Guvenlik Denetimi
Basarisiz
Health Uyari
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Basarisiz
  • rm -rf — Recursive force deletion command in .github/workflows/ci.yml
  • rm -rf — Recursive force deletion command in apps/api/package.json
  • process.env — Environment variable access in apps/api/scripts/local-usage-metrics.mjs
  • process.env — Environment variable access in apps/api/scripts/mcp-local-smoke.mjs
  • process.env — Environment variable access in apps/api/scripts/prepare-ci-db.mjs
  • process.env — Environment variable access in apps/api/scripts/support-workflow/reset.ts
  • process.env — Environment variable access in apps/api/scripts/support-workflow/seed.ts
  • network request — Outbound network request in apps/api/scripts/support-workflow/seed.ts
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

Open-source multi-tenant memory platform for AI agent teams — shared memory, MCP-native, self-hosted.

README.md

Monet

Turn your team's AI operational intelligence into a reusable asset.

License: Apache-2.0
GitHub Stars

Getting Started · Architecture · Documentation · Contributing


Senior developers get better AI results — not because of better prompts, but because of accumulated operational know-how. Monet captures that intelligence as shared memory, so your entire team benefits from the same AI expertise.

Monet is an open-source, multi-tenant memory platform for AI agents. It gives your agent team a shared memory layer that persists across sessions, agents, and team members — with native MCP support and true tenant isolation.

Why Monet?

The Problem How Monet Helps
Agents lose context between sessions Memories persist and are searchable across sessions
Senior dev AI know-how stays with individuals Operational intelligence is captured and shared with the team
Each agent starts from scratch Agents inherit accumulated team knowledge from day one
No visibility into what agents remember Dashboard UI for memory inspection and audit trails

Key Features

  • 🧠 Shared Memory for Agent Teams — Agents read and write to a shared memory layer scoped by group, user, or private access
  • 🔌 Native MCP Support — Connect any MCP-compatible agent with a single endpoint: /mcp/:tenantSlug
  • 🏢 True Multi-Tenant Isolation — PostgreSQL schema-level isolation per tenant, ready for SaaS and MSP use cases
  • 📊 Dashboard UI — Setup, tenant administration, and memory inspection at a glance
  • 🔍 Semantic Search — pgvector-powered embedding search with automatic enrichment (summaries, tags, vectors)
  • 📋 Audit Trail — Append-only audit logs with DB-level protection for compliance and observability
  • 🏠 Self-Hosted — Run on your infrastructure. No cloud lock-in. Your data stays yours.

Memory That Works Like Your Team

Monet organizes memories by type and scope, matching how teams actually think:

Memory Types: decision · pattern · issue · preference · fact · procedure

Memory Scopes:

Scope Who Sees It Use Case
group All agents in the group Shared team knowledge, best practices
user Agents serving a specific user User-specific context and preferences
private Only the authoring agent Agent-specific working notes
┌───────────────────────────────────────────────┐
│                  Tenant                       │
│                                               │
│  ┌───────────┐  ┌───────────┐  ┌───────────┐  │
│  │ Agent A   │  │ Agent B   │  │ Agent C   │  │
│  │ (Support) │  │ (Support) │  │ (Billing) │  │
│  └─────┬─────┘  └─────┬─────┘  └─────┬─────┘  │
│        │              │              │        │
│        ▼              ▼              ▼        │
│  ┌─────────────────────────────────────────┐  │
│  │           Shared Memory Layer           │  │
│  │                                         │  │
│  │  🔵 group scope   → visible to all      │  │
│  │  🟡 user scope    → per-user context    │  │
│  │  🔴 private scope → agent-only          │  │
│  └─────────────────────────────────────────┘  │
└───────────────────────────────────────────────┘

Getting Started

Prerequisites

Quick Start (Containers)

git clone https://github.com/team-monet/monet.git
cd monet
pnpm install
pnpm quickstart

This one command ensures runtime env/config, starts containers (postgres,
keycloak, migrate, api, dashboard), bootstraps Keycloak + demo tenant, and
prints ready-to-copy MCP config and local login details.

Then follow the full local setup guide:

Connect Your Agent (MCP)

Once Monet is running, connect any MCP-compatible agent:

Container quickstart (pnpm quickstart) defaults to API port 4301.

{
  "mcpServers": {
    "monet": {
      "url": "http://localhost:4301/mcp/demo",
      "headers": {
        "Authorization": "Bearer your-agent-api-key"
      }
    }
  }
}

Your agent now has access to these memory tools:

Tool What It Does
memory_store Store a new memory (decision, pattern, issue, preference, fact, procedure)
memory_search Search memories by semantic query, tags, or type
memory_fetch Fetch full memory content by ID
memory_update Update an existing memory with optimistic concurrency
memory_delete Delete a memory (author-restricted)
memory_promote_scope Promote a memory's visibility (e.g., private → group)
memory_mark_outdated Mark a memory as outdated
memory_list_tags List all tags used across memories

Architecture

Monet runs as a straightforward service stack designed for self-hosted deployment:

┌─────────────┐  ┌──────────────┐
│  Dashboard  │  │  API Service │── /api/tenants/:slug/...
│  (Next.js)  │  │              │── /mcp/:slug
└─────────────┘  └──────┬───────┘
                        │
        ┌───────────────┼──────────────┐
        │               │              │
   ┌────▼──────┐ ┌──────▼──────┐   ┌───▼─────┐
   │ PostgreSQL│ │  OIDC Auth  │   │ Enrich  │
   │ + pgvector│ │ (Keycloak)  │   │ Pipeline│
   └───────────┘ └─────────────┘   └─────────┘

Core design decisions:

  • Tenant-qualified routing — every request is scoped to a tenant via URL path
  • Schema isolation — per-tenant PostgreSQL schemas (tenant_<id>) with SET LOCAL search_path
  • MCP as a first-class citizen — dedicated endpoint, session lifecycle management, tool schema registry
  • Enrichment pipeline — automatic summary, tag extraction, and vector embedding on every memory write

Read the full architecture overview: docs/architecture/overview.md ->

Documentation

Start with the full docs index: docs/README.md

Guide What You'll Find
Local Development Set up a local dev environment
Architecture Overview System design, data model, MCP internals
Tenant Management Create and manage tenants
Platform Administration Platform setup and admin workflows
Production Deployment Deploy Monet to production
Observability Monitoring, logging, health checks
Backup & Restore Data backup and recovery procedures
Migration & Upgrade Version upgrades and schema migrations

Contributing

We welcome contributions! Start here:

Security

Please report vulnerabilities through private GitHub advisories (not public issues/PRs):

License

Monet is licensed under the Apache License 2.0. See LICENSE.


Built with the belief that AI operational intelligence should be a team asset, not an individual advantage.

⭐ Star us on GitHub · 🐛 Report a Bug · 💬 Start a Discussion

Yorumlar (0)

Sonuc bulunamadi