Self-host Manor AI
v0.1.1AI agent workspace for governed agents and tools
- Stars
- 158
- Ports
- 80 (Web frontend (nginx) - proxies /api to API container), 8000 (FastAPI application (internal)), 5432 (PostgreSQL with pgvector (internal)), 6379 (Redis cache, Celery broker, rate limits, JuiceFS metadata (internal)), 9000 (MinIO S3 API (internal)), 9001 (MinIO Console (internal)), 8200 (Vault transit backend for secrets encryption (internal)), 11434 (Ollama local embedding model server (internal)), 3003 (Nango OAuth aggregator server (nango profile, internal)), 8800 (WeChat Personal runner (wechat profile, internal))
- Requires
- Minio, Ollama, PostgreSQL 16 with pgvector, Redis, Sandbox service, Vault
What is Manor AI?
Manor AI is a source-available AI workspace that teams can host themselves. It targets small companies and solo operators who want persistent AI agents that remember context across sessions. The stack combines a React frontend with a FastAPI backend, Celery task workers, and a sandbox for running code safely. Operators supply their own LLM API keys so no data leaves their environment. Governance features include approval gates, scoped tool access, and audit trails. Documents are stored in MinIO and indexed with pgvector for retrieval. The platform connects to dozens of external services through OAuth, webhooks, and the Nango aggregator. Deployment uses Docker Compose with PostgreSQL, Redis, Vault, and Ollama for local embeddings. The license allows internal and personal use but forbids reselling hosted access.
Should you self-host Manor AI?
Manor AI scores 39/100 on selfhost.directory (how scoring works) and ranks #170 of 209 in AI Agents. It has 158 GitHub stars.
It shipped 2 stable releases in the past year. The latest, v0.1.1, came out on 12 October 2026. New versions land roughly every 3 months.
Setup is advanced: plan for several services and some ongoing maintenance. It is Other-licensed and written mostly in Python.
Its closest alternative on selfhost.directory is Orca (91/100, 108 898 stars). It scores higher overall, so compare the two before you pick. See Manor AI vs Orca side by side.
Features
- Agent Runtime
- AI Workspace
- Blueprints
- BYOK Model Access
- Collaboration & CRM
- Extensibility
- Human-in-the-Loop Governance
- Integrations
- Knowledge and Files
- Live Voice CallsRequires native OpenAI BYOK key configured in Account → Models
- Local Embeddings (Ollama)
- Operations Tooling
- PowerPoint Generation
- Sandbox isolation
Manor AI README
FAQ
Is my data safe with Manor AI?
Yes. Your data is encrypted in transit and at rest, never used to train models, and you can export or delete your workspace at any time. You own everything that goes in.
Can creators sell AI workspaces on Manor?
Yes. In Manor Cloud, creators can build and test a workspace, export it as a Blueprint, connect a payout account, set a one-time price, submit the paid listing for review, and earn seller proceeds when buyers purchase it.
Does Manor AI offer a free AI consulting session?
Yes, a free 30-minute initial AI consulting session about custom AI workspace implementation, agents, reusable skills, workflow automation, knowledge bases, approvals, and pilots for your team.
How much does Manor AI cost?
Costs can include a one-time paid template purchase plus model and tool runtime usage. Self-hosted use has its own hosting and model costs. Manor Cloud starts free, then Personal at $20/month and Pro at $49/month.
Do I need to know how to code?
No. You can configure instructions, source material, and supported connections without writing code. Setup still depends on the tools and permissions your workflow needs.
What should a solopreneur automate first with AI agents?
Start with repetitive, high-volume, easy-to-review workflows: inbox triage, follow-up drafts, meeting summaries, lead qualification, customer support routing, document search, and weekly reports. Keep final customer-facing actions behind human approval until proven.
Can Manor AI work with n8n workflows?
Manor AI is designed around agents, skills, and workspaces first, with future compatibility for workflow systems such as n8n. The goal is to keep business context, approvals, and logs in Manor while connecting to deterministic workflows where they make sense.
Is Manor AI like n8n?
Manor AI and n8n both help businesses automate work but at different layers. n8n is a workflow automation builder for explicit steps and integrations. Manor AI is an AI business workspace for agents, business context, reusable skills, approvals, and human-reviewed actions.
How is Manor AI different from ChatGPT?
ChatGPT is a general AI assistant. Manor stores sources, configuration, and results for recurring business work, and can prepare drafts or take supported connected actions subject to configured permissions and review.
Is Manor AI mainly an AI agent builder?
Manor AI is primarily a long-running AI business workspace, though teams can build an agent for a specific job. The workspace preserves settings and results for reuse.
Can Manor AI generate PowerPoint slide decks?
Yes, Manor AI can generate editable PPTX slide decks from prompts, notes, Markdown, business briefs, or provided source text for pitch decks, client proposals, workflow maps, business reports, launch plans, and internal updates.
What can Manor's agents actually do?
Agents can search company knowledge with citations, prepare drafts and reports, create follow-up tasks, and run configured recurring workflows using connected documents and supported tools.
What is an AI business workspace?
A persistent operating layer where agents continue working from durable goals, company knowledge, connected tools, schedules, approvals, citations, and activity history over time.
Who is Manor AI built for?
Solo founders, indie hackers, small agencies, property managers — teams of 1–20 people who are tired of being the bottleneck for every routine task.
What is Manor AI, really?
Manor is a long-running AI business workspace that keeps goals, company context, agents, schedules, approvals, and work history connected so recurring back-office work can continue across days and months.
More in AI Workflows
markusSelf-hosted open-source AI workforce platform running autonomous agent teams locally with your own API keys.
self-hosted-ai-starter-kitThis open-source Docker Compose template spins up a self-hosted AI stack with n8n, Ollama, Qdrant and PostgreSQL, auto-pulling Llama3.2 for local workflows.
SimOpen-source, self-hosted AI workspace for teams designing, launching and observing agent workflows, with 1,000+ app connectors, tables, knowledge bases and run logs.
1flowbaseAn open-source AI Gateway and app runtime you host yourself, unifying model access with PostgreSQL storage, workflows, APIs, and React apps via MCP.
AgentaOpen-source, self-hosted workspace where teams build AI agents by chatting, run them in Slack, Telegram or WhatsApp, and schedule automations on any LLM.
bifrostOpen-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.
bishengAn Apache-2.0, self-hosted LLM devops platform for enterprise AI: GenAI workflows, RAG knowledge bases, agents, model management, evaluation, SFT and OCR.
DEEIX ChatDEEIX Chat is a self-hosted, open-source AI workspace unifying model routing, multimodal chat, RAG, MCP tools, billing, and identity into one deployable platform.
deer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
difyDify is a self-hosted, open-source LLM app platform with visual workflows, RAG pipelines, agents, and model management for taking AI apps from prototype to production.
duragraphDuraGraph is a self-hosted, open-source control plane for durable AI agent workflows. It uses event sourcing and CQRS to make every run replayable and crash-safe.
EigentOpen-source desktop app to run single agents or multi-agent workforces; self-host the FastAPI backend with Docker and use any cloud or local model.
0 comments