Open-source experiments · MIT licensed · Built in the open

The experiment lab
for the agentic era

NorviaLabs ships a family of focused open-source experiments for AI builders — runtimes, observability, research harnesses, and developer tooling. Small sharp ideas. Public by default. MIT throughout.

12
Open experiments
5
Product families
0
Accounts required
MIT
Licensed throughout

An open-source lab for experiments that should have been public sooner

AI teams ship agents faster than the tooling underneath them can keep up. Evaluations are fragile, observability is afterthought glue, and half the “research” never leaves a private notebook.

NorviaLabs publishes that missing layer as focused, MIT-licensed experiments. Sometimes it is a runtime primitive — a sandbox, a memory shard, a trace kit. Sometimes it is a research harness or a small tool that makes the next experiment cheaper to run. Each one does one thing well and lives in the open.

experiment.py
# Small imports. Sharp ideas. Ship in the open.
from tracekit import Tracer
from sandbox_lite import Sandbox
from costmap import CostMap

tracer = Tracer()
with Sandbox(timeout=30) as box:
    result = box.run(agent_step)
    tracer.span("agent_step", result)

CostMap.from_run(tracer).print()  # where did tokens go?

Open experiments, one thesis

Each experiment encodes one sharp idea, ships its own docs, and is free to fork. Filter by what you are building.

No experiments in this family yet.

See all experiments →

Five families across the experiment stack

Every experiment fits into one of them.

If you need this, reach for that

A decision table across the portfolio. Match your problem to the experiment built for it.

If you need to… Reach for Family Stack

The same principles run through every experiment

1

Public by default

Experiments start open. Source, issues, and notes ship together so others can reproduce, fork, or kill the idea honestly.

2

One sharp idea each

Small products that do one thing well and compose. No kitchen-sink frameworks — just a clear README and a hard boundary.

3

Measure what matters

Benchmarks, traces, and cost maps are first-class. If we cannot measure it, it is not ready to recommend.

4

MIT, no lock-in

Every experiment is MIT licensed. No accounts, no telemetry tax, no closed tiers — the library or CLI is the whole thing.

Start with a single experiment

All NorviaLabs projects are open source and MIT licensed. Every README, changelog, and benchmark is in the open.

Frequently asked questions

What is NorviaLabs?
NorviaLabs is an open-source experiment lab building focused tools for AI builders. We ship MIT-licensed projects across foundations, runtimes, observability, tooling, and research — each encoding one sharp idea.
Is everything open source?
Yes. Experiments are MIT licensed and public on GitHub. There are no closed product tiers today — the CLI or library is the whole thing.
How do I choose an experiment?
Start from the problem. Use the “Find a tool” decision table on this page, or filter the portfolio by family (Foundations, Runtimes, Observability, Tooling, Research).
Can I contribute?
Absolutely. Open an issue or PR on the relevant repository under github.com/norvialabs. Small, well-scoped changes and reproducible bug reports are especially welcome.
How is this different from a product company site?
NorviaLabs is a lab, not a SaaS catalog. Experiments may graduate, pivot, or be archived in public. The goal is useful software and honest learning — not a sales funnel.