Context Layer for Odoo
Current limitations.
The honest edges of early access: what is experimental, unreleased, or deliberately not claimed. Read this before building on OCL so expectations match what is actually proven today.
This is a self-serve developer early access, on a v0 format that can still change. It is substantial and honest, which means being clear about its edges. None of the following is a bug; it is the current state.
Scope
- Odoo 19 only. Community and Enterprise, stock. Odoo 17, 18, and any future version are not supported or advertised.
- Focused coverage. 171 verified entries is focused coverage, not complete coverage of Accounting, Sales, Inventory, or Purchase. See Coverage and release status.
- Stock-scoped claims. Released facts are proven against stock Odoo 19. Custom modules, localizations, tenant policy, access rules, company, and currency can change the correct answer for a specific database. Resolving those is the job of the tenant overlay, which is a foundation, not a finished product.
The tenant system
- The tenant system (overlay, memory, drift, governed memory, export and deletion audit, isolation) is an implemented local-alpha foundation, not a hosted commercial product. The hosted workflow, the review UI, production security controls, and real pilots are still ahead.
Benchmark
- Live model runs exist, but independent blind human scoring is pending. Until it is complete and passing, there is no published accuracy figure, no chart, and no “gate passed” claim. See Benchmark methodology.
Distribution
- The open standard is public at github.com/Nantiai/ocl-standard (Apache-2.0): the format, validator, conformance suite, reference source clients, ten candidate example entries, and an example MCP server. See the Quickstart.
- The verified 171-entry runtime is live at
api.context.nanti.ai, self-serve on a free 7-day trial: one email issues a universal, expiring key on the spot that covers both Odoo 19 editions, all released modules, and all five operations over authenticated REST or remote MCP. The trial runs without a request-count meter, but burst, context-size, and anti-extraction limits stay active, the 171-entry registry is not downloadable or enumerable, and there is no production SLA. The reference clients are source, not published PyPI or npm packages. - What is genuinely not public: the raw verified corpus and its evidence, the verification harness, the private retrieval index and ranking, and the tenant overlay and memory. Alpha access does not grant redistribution or production embedding, which is a separate licensed conversation.
What OCL does not promise
The hard limits
OCL is interpretation infrastructure. It does not:
- eliminate hallucinations, or guarantee any AI answer is correct;
- make an AI-generated write automatically safe (write-intent validation is advisory and never authorizes);
- replace or weaken Odoo permissions, record rules, or business methods;
- self-verify. Machine-testable rules and applicability are executed; meaning that cannot be machine-tested relies on attributable evidence or authorized review.
Naming
- “Context layer” and “OCL” are working category labels, not a final product name. Final naming is deferred to a trademark review. Odoo is a trademark of Odoo S.A.
Getting access
Start today with the open standard: clone github.com/Nantiai/ocl-standard and follow the Quickstart. For the verified runtime, try one decision with no login at the demo, then start a free 7-day trial. One email, and the universal key appears on the spot.