Self-hosted AI workforce
Your AI workforce.
Self-hosted in 60 seconds.
Pre-configured AI hires that handle real work in Gmail, Slack, HubSpot, and 16 more tools. Run on your own infrastructure with one Docker command.
Hosted from $1,999/mo · Self-host from $4,900 · Turnkey hardware available
Dashboard
What needs attention, what's been happening, system health.
Workforce
All clear — nothing failing or overdue.
5/5 connected · Discord, Slack, Email, Web, Telegram
You're hiring slower than you're growing.
Your SDR team can't keep up with inbound. Support is drowning in tickets that have known answers. Billing is shipping past their SLA. The work doubles every quarter and headcount can't follow.
Closed AI platforms (Salesforce Einstein, Microsoft Copilot, ChatGPT for Work) want all your data in their cloud, charge per token, and lock you into their ecosystem. That's not an option in regulated industries.
Inhouse Agents is the alternative — pre-configured AI staff you self-host, integrate with your existing tools, and own end-to-end.
8 pre-configured AI hires
Each role ships with a job description, a set of skills, and a heartbeat — recurring work it does on its own.
SDR
Prospects, researches, and initiates outbound to book meetings.
Support Agent
First-response triage, resolution of known issues, knowledge-base lookups.
Billing Coordinator
Invoicing, dunning, refund processing, failed-payment recovery.
Executive Assistant
Scheduling and inbox triage — proposes times, books meetings, drafts replies.
Research Analyst
Briefs, memos, competitor teardowns, charted findings.
Product Manager
Coordinates a delegation team — hands UI to Designer, planning to TPM.
Designer
Translates briefs into concrete UI/UX specs. Pairs with Product.
Technical PM
Turns briefs into sprint plans and RFC outlines. Pairs with Product.
From zero to working in three steps
No new tooling to learn. No data leaving your network. No per-token surprises.
Install
One Docker run. Pick local Ollama, OpenRouter, or any OpenAI-compatible endpoint.
docker run -p 3100:3100 \
inhouse/agents:latestConnect your tools
OAuth into Gmail, Slack, HubSpot, Salesforce. Or paste an API key for the rest. Capability slots map to your stack.
Pick a team, click install
Choose a Role or a Team Pack. Agents come online with delegation pre-wired and start their heartbeat work immediately.
Built for real ops teams
Everything you need to run a working AI workforce in production — without giving up control.
Roles
Pre-built agent templates — system prompt, tools, and a heartbeat (recurring work it does on its own).
Teams
Multi-agent bundles with delegation pre-wired. One click installs the org chart.
Capability Slots
Agents declare abstract needs (CRM, email send, scheduling). Bind to whatever tools you already use.
OAuth
BYO-app OAuth for Google, Microsoft, Salesforce, Slack, HubSpot. Tokens encrypted on disk.
Triggers
Webhook in, agent fires. Wire any vendor (Stripe, Linear, Zendesk) with templated prompts.
Observability
Per-agent token + cost tracking. See who did what, where the time went, what it cost.
Why self-host?
Closed AI platforms work for hobbyists. Real ops teams need privacy, predictable cost, and control.
Privacy
Your customer data never leaves your network. Run on local Ollama; the only outbound traffic is to the SaaS apps your agents already touch.
Cost
Local models cost $0 per token after the GPU. Or use OpenRouter and pay wholesale. No usage-based platform fees on top.
Control
Edit the system prompt. Swap the model. Strip a tool from a channel. Audit every action via per-agent activity logs.
Not ready for a call?
Drop a quick brief and we'll send you a tailored example for your workflow within 24 hours.
Ready to hire your first AI agent?
15 minutes. We'll walk through the install and answer your hardest "but what about…" question.
Book a 15-min demo →Existing customer? Sign in to your console