Solutions Factory · CRM
The CRM where agents do the data entry, not the rep.
Self-hosted and licensed to you. A Pipedrive-equivalent surface with four agents running on your own APG appliance — keeping the pipeline complete while the inference stays metered, itemized, and in a jurisdiction you choose.
The problem
Data entry is the part nobody does.
Ask any sales manager what proportion of their CRM records are complete and current, and watch the pause before the answer. The cause is not laziness. Data entry is the least rewarding part of a rep's day, so it slips to 5pm on Friday, or it never happens at all. The forecast inherits the gaps.
The cloud CRMs answer this with AI tiers priced at $30 to $150 per user per month, and the results disappoint. Self-hosted open-source CRMs like Twenty and EspoCRM own data sovereignty but ship no agent automation, so the manual entry stays manual.
Privacy-sensitive teams carry a second problem. Legal, healthcare, and financial-advisory practices often cannot host a client pipeline on US cloud at all. They need the pipeline on their own infrastructure, in their own jurisdiction, with no exceptions to negotiate.
What it does
A full CRM as the floor. Agents on top.
The Pipedrive-equivalent feature surface is the starting point, not the pitch. Everything a sales team expects, self-hosted and yours.
- Contacts and companies with custom fields and tags.
- Pipeline kanban with drag-to-stage and weighted value.
- Activities and tasks tied to every record.
- Reports on pipeline, velocity, and conversion.
- CSV import and export with no row caps.
- Signed webhooks and a full REST API with tokens.
- Public forms that write straight to the pipeline.
- Multi-tenant isolation enforced at three layers.
Self-host from the licensed release
# your data never leaves this machine $ tar xzf solutions-factory-crm.tar.gz $ cd solutions-factory-crm $ docker compose up -d CRM ready at http://localhost:8080 · agents bound to APG runtime
How the agents work
Four agents, running on your APG appliance.
Each agent runs on your own APG runtime, under the same cost ceilings, health checks, and operator-confirm gates as everything else on APG. Inference is metered and itemized at Tier 1, your own key at Tier 2, or sovereign on your GPU at Tier 3.
The data clerk
Deduplicates, enriches and flags stale records continuously. This is the one that makes the pipeline trustworthy without a rep typing into it.
The inbox triager
Reads what arrives, classifies it against the pipeline, and drafts the reply. A person approves before anything sends.
The pipeline auditor
Flags stalled deals, reports what actually moved this week, and keeps stage definitions honest so the forecast means something.
The briefer
Assembles a one-page account brief before the call, out of records you already hold.
Why these are drawn as graphs, not loops
An agent left in an open loop is asked to keep going until it decides it is done. That is the right shape for exploration and the wrong shape for a pipeline that has to behave the same way every Tuesday.
Recurring work is drawn as a graph instead: named nodes, declared inputs and outputs, one edge to the next step. Every node can be tested on its own, replayed against last week's data, and pointed at a different model without touching the ones around it. When something goes wrong you get the node that failed rather than a transcript to read.
The four agents above are graphs. Where judgement genuinely needs room, the loop stays — inside a single node, with a cost ceiling and a person on the far side of it.
What it costs
Flat software fee, inference itemized.
Self-host
A flat software fee. You run it on your own infrastructure and hold the database.
Managed
Flat per workspace, per month. We operate it on infrastructure you authorize, with SLAs.
Inference
Separate and itemized: SF default (per token), your own Anthropic key, or sovereign on your GPU.
Why self-hosted, by you
The only CRM where the inference is itemized like an electricity bill and the agent does the data entry.
The pipeline — every contact, every deal, every note — sits in your database, in your jurisdiction, under your backup policy. The agents run on your APG appliance, and the inference behind them is a line item you can read, not a mystery bundled into a per-seat price. Dial it from metered to sovereign as your privacy posture demands.
Technical fact sheet
For the operator evaluating the stack.
- Stack
- Node 22 LTS, TypeScript in strict mode, Zod validation at every domain boundary, JWT auth.
- Data plane
- SQLite via
node:sqliteby default; a Postgres adapter for SaaS scale. Eight migrations. - Agents
- Four, running on your APG runtime under its cost ceilings, health checks, and operator-confirm gates.
- Inference
- SF default (Tier 1, metered + itemized), BYOK Anthropic (Tier 2), or sovereign ollama (Tier 3).
- Frontend
- No build step — HTML, vanilla JS. The deploy artifact is source.
- Licence
- Commercial licence to the client. Private repository; no open-source grant.
- Deployment
- Docker and docker-compose, plus four platform deploy configs (Coolify, Railway, Render, Fly).
- Integrations
- Full REST API with an OpenAPI 3 spec, signed webhooks, public forms, API tokens, CSV.
- Isolation
- A load-bearing multi-tenant isolation contract test blocks any cross-tenant read.
- Status
- V1 shipped 2026-05-29. V2 in flight: email integration, workflow rules engine, browser extension, DocuSign, Stripe billing, Postgres adapter, mobile PWA, accessibility hardening.
How it compares
Against HubSpot and Pipedrive.
Plain comparison on the axes that decide it for a cost-pressured, privacy-conscious team.
| Capability | Solutions Factory CRM | HubSpot | Pipedrive |
|---|---|---|---|
| Hosting | Self-host or managed | Cloud only | Cloud only |
| Data residency | Your database, your jurisdiction | Vendor cloud | Vendor cloud |
| Pricing model | Flat software + itemized inference | Per seat, per month | Per seat, per month |
| AI agents | Four, on APG | Add-on tier | Limited add-on |
| Inference cost | Metered + itemized, or your own GPU | Bundled / opaque | Bundled / opaque |
| Where it runs | Your infrastructure, your database | Vendor cloud | Vendor cloud |
| API | Full REST + OpenAPI 3 | Yes | Yes |
Reference deployments
Honest about the stage.
The CRM shipped V1 on 2026-05-29. Early tenant deployments are landing now; we will name them here as they go to production and agree to be referenced. We would rather show a real early deployment than a fake logo wall.
Get started
Self-host the CRM in under an hour.
Clone it, run one command, and bind its agents to your own APG runtime. Or talk to us about a managed deployment.