Open Source Strategy
Ody is built with a clear open-core model. The knowledge quality tools are free; the training pipeline and AI assistant are proprietary.
License Map
| Component | Package | License | Purpose |
|---|---|---|---|
| Platform Core | @useody/platform-core | Apache 2.0 | Types, SQLite, providers, vector index |
| Detectors | @useody/detectors | Apache 2.0 | 5 detectors + consultant analysis + consensus |
| Eval | @useody/eval | Apache 2.0 | Benchmarks, corpus runner, flywheel test |
| Export | @useody/export | Apache 2.0 | HTML report, JSONL, TRL adapter, tickets |
| Refine CLI | ody-refine | Apache 2.0 | The free wedge -- scan, detect, resolve, export |
| Forge CLI | proprietary | Proprietary | Training pipeline, model registry |
| Feedback | proprietary | Proprietary | Signal collector, reputation, reward derivation |
| Training | proprietary | Proprietary | Dataset registry, model registry, orchestrator |
| Colleague | proprietary | Proprietary | Web app, API, Slack bot, worker |
Repository Structure
| Repo | License | What's inside |
|---|---|---|
platform/ | Apache 2.0 (public) | Core libs, detectors, eval, export, Refine CLI |
forge/ | Proprietary | Training, feedback, Forge CLI |
colleague/ | Proprietary | Web app, API, Slack bot, background worker |
Why Open Source Refine?
Refine is the wedge. It provides immediate value (find broken docs in 2 minutes) with zero commitment. The health report is the viral moment -- teams share it, star the repo, and discover the rest of the platform.
The open source components are genuinely useful on their own:
- Run
ody-refinein CI to catch docs drift - Use detectors in your own tools
- Export findings as tickets or training data
- Generate health badges for your README
What Stays Proprietary
The training pipeline and AI assistant are proprietary because they are the revenue products:
- Forge charges for managed training (GPU compute, model hosting)
- Colleague charges per seat and consumption (the daily-use product)
Shared Contract
The @useody/* npm packages define the interface between open and proprietary:
@useody/platform-core-- types, document model, provider interfaces@useody/eval-- benchmark definitions, evaluation framework
These packages are published under Apache 2.0 so anyone can build on top of Ody's detection and evaluation primitives.
Competitive Position
Nobody does what Ody does. The market validates adjacent problems:
| Competitor | What they do | What they don't do |
|---|---|---|
| Airweave | Context retrieval for agents | No integrity layer |
| HydraDB | Ontology-first context graph | Infrastructure, not product |
| Mintlify | Docs formatting CI | Not content trustworthiness |
| Glean/Guru | Search enterprise knowledge | No training loop |
Ody's lane: Context integrity -- the quality gate between messy company knowledge and AI that acts on it.