Feature hasn't been suggested before.
Describe the enhancement you want to request
The problem
altimate-code is excellent when you can run it directly. But a growing number of dbt teams are standardized on subscription harnesses — Claude Code, Cursor, Windsurf — where company policy or cost constraints mean only one LLM is allowed to run.
The users most likely to want altimate-code's SQL intelligence — dbt teams at companies with strict tooling governance — are exactly the ones who can't use it today. This is a real adoption blocker.
The proposal
Ship an official subscription-adapter plugin alongside altimate-code: a thin harness layer that exposes altimate-core's deterministic engine to model-locked environments via the Model Context Protocol (MCP), with the altimate LLM agent never invoked.
Users in those environments would:
- Install the plugin — one
npm install, one init command
- Get the same Rust/NAPI engine altimate-code uses: transpile, lint, lineage, PII check, equivalence, schema diff, dbt PR review with a signed verdict, impact analysis, finops, and more
- Get skills and agent personas scaffolded directly into their harness
- Never need an altimate API key or a second model
The altimate-code agent would be explicitly forbidden at the code level, not just undocumented. Users get the deterministic half of altimate-code only.
Prior art — proof of concept
I built a proof-of-concept called opende that implements exactly this. It exists because the gap is real and there was no official path.
| What |
Detail |
| Test coverage |
228 passing tests (unit + integration against the real engine) |
| MCP tools |
64 tools exposed via opende-mcp |
| CLI entry point |
interactive opende init wizard |
| Core dependency |
@altimateai/altimate-core, currently tracking 0.6.0 |
| Harness support |
Claude Code today; adapter-based CLI generator makes Cursor/Windsurf a thin addition |
| License |
MIT, with full attribution to altimate-code and altimate-core in NOTICE |
A community fork tracking your core library is a worse outcome for everyone than an official plugin — version drift, inconsistent verdicts, confused users. The goal of this issue is to find a better path.
What I'm asking
I'd like to discuss whether Altimate would be interested in any of these:
- Adopting this as an official plugin — maintained under the altimate-code org, with opende merged or superseded by an official implementation
- Co-maintaining it — opende stays independent but is officially acknowledged and linked as the supported path for subscription-locked users
- Committing to a stable public API surface in
altimate-core — so community adapters can track releases without breakage
Happy to share more about the implementation, contribute code directly, or help design the integration. The demand is real — I built this because my own team needed it.
Reference implementation: https://github.com/lgwacker/opende
Feature hasn't been suggested before.
Describe the enhancement you want to request
The problem
altimate-code is excellent when you can run it directly. But a growing number of dbt teams are standardized on subscription harnesses — Claude Code, Cursor, Windsurf — where company policy or cost constraints mean only one LLM is allowed to run.
The users most likely to want altimate-code's SQL intelligence — dbt teams at companies with strict tooling governance — are exactly the ones who can't use it today. This is a real adoption blocker.
The proposal
Ship an official subscription-adapter plugin alongside altimate-code: a thin harness layer that exposes
altimate-core's deterministic engine to model-locked environments via the Model Context Protocol (MCP), with the altimate LLM agent never invoked.Users in those environments would:
npm install, oneinitcommandThe altimate-code agent would be explicitly forbidden at the code level, not just undocumented. Users get the deterministic half of altimate-code only.
Prior art — proof of concept
I built a proof-of-concept called opende that implements exactly this. It exists because the gap is real and there was no official path.
opende-mcpopende initwizard@altimateai/altimate-core, currently tracking0.6.0What I'm asking
I'd like to discuss whether Altimate would be interested in any of these:
altimate-core— so community adapters can track releases without breakageHappy to share more about the implementation, contribute code directly, or help design the integration. The demand is real — I built this because my own team needed it.
Reference implementation: https://github.com/lgwacker/opende