01
Active guardrails
Rules and constraints injected into every prompt. The agent can't ignore them because they travel with each model call: tone, scope, forbidden actions and goals, always present.
Early access · In production
AI agents you can audit line by line
Open source fork of nano-bot, hardened with active guardrails, path-level access control and embedded audit logging. Official Docker images for deployment — coming soon.
Minerva Workbench
Internal architecture
An autonomous agent, but under control
We start from nano-bot, the autonomous agent from the University of Hong Kong, and harden it with four Minerva layers so it can operate in real environments without surprises. Everything is open source. Official Docker images for deployment are coming soon.
Built on nano-bot (HKU) 100% open source · Permissive license
- 01
Active guardrails
Rules and constraints injected into every prompt.
- 02
Path access control
Allow/deny list of editable paths.
- 03
Full auditability
Every interaction is normalized and stored in a SQLite database embedded in the agent itself.
- 04
Operator UI
Built-in UI to edit any file in the workspace, chat with the agent, validate intermediate actions, and query the SQLite audit log — all in one place.
Four layers so the agent never drifts off-script
We don't trust the model's good will. We lock it inside clear rails and record every step.
02
Path access control
Allow/deny list of editable paths. You define what the agent can read, write or ignore. It cannot touch anything outside its authorized workspace.
03
Full auditability
Every interaction is normalized and stored in a SQLite database embedded in the agent itself. Full traceability: prompts, responses, tools used, file changes.
04
Operator UI
Built-in UI to edit any file in the workspace, chat with the agent, validate intermediate actions, and query the SQLite audit log — all in one place.
What teams ship with Stands
Three production deployments with Minerva customers—not slideware. Each agent owns a full workflow: calendar and inbox, social content, or customer memory.
Live
Calendar & email manager
A digital secretary with access to the calendar and inbox. Prioritizes and categorizes emails based on whether they need action, oversight, are blocking something, or are purely informational.
- Instant alerts for high-priority actions
- Bulk-edit queue for the rest, sorted by category
- Drafts ready-to-send responses for your review
Live
Autonomous marketing manager
Once a day it scrapes news relevant to the company, extracts topics with cited sources, and after user approval writes, reviews and schedules content across social networks.
- Daily topics with verifiable sources
- Automated post drafting and review
- Generated infographics and multi-channel scheduling
Live
Customer knowledge guardian
Active memory with a custom protocol and Minerva's internal tooling. Categorizes and keeps every customer interaction, demo and commitment up to date, wired into Google Calendar.
- Active per-customer memory with accumulated context
- Creates events and blocks on Google Calendar
- Generates internal briefings so the whole team stays aligned
Open code, deployed on your infrastructure
We believe autonomous agents should only run if they can be audited. Minerva Stands is open source end-to-end. Official Docker images are coming soon so you can inspect, modify, and choose where it runs.
View on GitHub- 100% open source — audit every line, no black boxes
- Official Docker images — coming soon (deploy on your cloud or ours when released)
- No vendor lock-in: keep it and operate it yourself if you want
Transparent price, flexible model
Pay setup once. Maintenance is optional if you have the engineering muscle to run it yourself.
Setup
One-timeFrom €1,600
Process consulting, agent design and initial deployment.
- Process definition consulting
- Guardrail and access-control design
- Agent configuration and deployment
- Team training and documentation handover
Maintenance
OptionalFrom €199 / month
Managed hosting, monitoring and agent evolution.
- Hosting on Minerva infrastructure
- 24/7 monitoring and alerting
- Continuous improvements and updates
- Priority technical support
Prefer self-hosting?
After setup you can keep the deployment on your own server and skip maintenance entirely. The code is yours. Official Docker images for self-hosted runs — coming soon.
Ready to deploy your first auditable agent?
Tell us the process you want to automate. In 30 minutes we'll tell you if Stands fits and what would make sense to build.