“Local” has more than one boundary
An AI coding setup can involve source files, an embedding model, a vector index, an assistant provider, and the host application that connects them. Saying that one component is local does not establish that the whole workflow is local.
SocratiCode’s local-only configuration covers its indexing and search path. The coding assistant remains a separate system with its own settings and terms.
Indexing path
Source chunks → local Ollama → local Qdrant
Assistant path
Prompt + selected tool results → assistant provider, according to that host’s settings
Review both paths before using sensitive source.
Keep SocratiCode indexing and search on the machine
This setup needs Node.js 18.17 or newer with npx, running Docker, and a running native Ollama installation.
Set these variables on the SocratiCode MCP server before its first index:
OLLAMA_MODE=external
OLLAMA_URL=http://localhost:11434
Leave EMBEDDING_PROVIDER, EMBEDDING_MODEL, and QDRANT_MODE unset. The defaults select Ollama, nomic-embed-text, and managed local Qdrant. Restart the MCP server after changing its environment.
Open the source project and call codebase_health, then codebase_index. The embedding model downloads on first use if it is not already present. Check codebase_status until indexing completes, then run codebase_search for a feature you know exists.
The default watcher keeps the index current while the process is running.
What remains on the network
The initial npm package, Docker image, and model downloads require network access. Those downloads are different from sending project source to a remote embedding provider, but they still matter in a restricted environment.
The assistant boundary is also separate. Depending on the selected host and model provider, prompts and SocratiCode tool results may leave the machine. A local embedding model does not change that provider’s behaviour.
If the organisation uses external Qdrant, a cloud embedding provider, or a managed assistant, document each endpoint and the data sent to it. Avoid collapsing them into one “AI tool” box during review.
Existing indexes need deliberate handling
Changing embedding settings does not silently convert vectors already stored under another profile. Before changing provider, model, dimensions, or indexed representation, inspect the effective index profile and follow the project’s documented re-index path.
This matters because an apparently healthy process can still be pointing at an index produced with incompatible settings. Failure should stay visible rather than being treated as an empty search result.
A boundary checklist for approval
- Where is the source checkout read?
- Which process receives source chunks for embedding?
- Where are vectors and index metadata stored?
- Which credentials protect any external index?
- What content does the assistant host send to its model provider?
- Can tool results contain sensitive source excerpts?
- Which downloads or update checks still require internet access?
- Who can query the resulting index?
- How are deletion, retention, and re-indexing handled?
Open source and Cloud beta are different reviews
The open-source local path can be inspected and operated directly. SocratiCode Cloud is a private beta and introduces a managed service boundary. Treat it as a separate deployment review. Availability, data flow, and controls for a proposed Cloud environment should be confirmed during onboarding, not inferred from the local setup.
For team-wide operation, continue with shared team context. For an authorised review workflow, use security review context.