惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

D
DataBreaches.Net
B
Blog
博客园_首页
C
Check Point Blog
Microsoft Security Blog
Microsoft Security Blog
MyScale Blog
MyScale Blog
P
Proofpoint News Feed
Engineering at Meta
Engineering at Meta
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
B
Blog RSS Feed
M
MIT News - Artificial intelligence
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
WordPress大学
WordPress大学
宝玉的分享
宝玉的分享
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
The Cloudflare Blog
量子位
V
V2EX
Y
Y Combinator Blog
Hugging Face - Blog
Hugging Face - Blog
Martin Fowler
Martin Fowler
Recent Announcements
Recent Announcements
I
InfoQ
博客园 - 【当耐特】

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
GitHub - team-monet/monet
johnonlee · 2026-04-29 · via Hacker News - Newest: "AI"

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 (Local)

git clone https://github.com/team-monet/monet.git
cd monet
pnpm install
cp .env.local-dev.example .env.local-dev
pnpm local:up

Then follow the full local setup guide:

Connect Your Agent (MCP)

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

{
  "mcpServers": {
    "monet": {
      "url": "http://localhost:3301/mcp/your-tenant",
      "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

Quick API Example

# Store a memory
curl -X POST http://localhost:3301/api/tenants/acme/memories \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "Always use pagination for list endpoints. Limit default is 50.",
    "memoryType": "pattern",
    "memoryScope": "group",
    "tags": ["api", "best-practice", "pagination"]
  }'

# Search memories
curl "http://localhost:3301/api/tenants/acme/memories?query=pagination+best+practice&limit=5" \
  -H "Authorization: Bearer $API_KEY"

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.md →

Production Deployment

Monet is designed for single-host Docker Compose deployment — no Kubernetes required:

cp .env.runtime.example .env.runtime
docker compose -f docker-compose.runtime.yml up -d

Documentation

Guide What You'll Find
Local Development Set up a local dev environment
Production Deployment Deploy Monet to production
Tenant Management Create and manage tenants
Platform Administration Platform setup and admin workflows
Architecture Overview System design, data model, MCP internals
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.