sf-intelligence

Ask questions about your Salesforce org in plain language — and get answers grounded in the org's real metadata, not a guess.

sf-intelligence is an offline, read-only, MCP-first knowledge base for a single Salesforce org. You run one retrieve (sf project retrieve); it builds a local Markdown vault and a DuckDB dependency graph. From then on every answer is served locally by default — offline-first, no network egress for vault answers. An opt-in live read-only plane (sfi.live_*) can answer record counts and samples when enabled. Private by design. MIT + Commons Clause.

Ask it like a person

You don't need to know the exact API name of anything. The front door is a typo-tolerant resolver that turns messy phrasing into the right component — and when it isn't sure, it asks you a clarifying question instead of guessing:

You: where's the emale field?

It: I found several matches for "email" — which did you mean? · Email__c on Account · Email__c on Contact · Alternate_Email__c on Lead

You: what about the paymnet object?

It: Payment__c — one confident match.

You: is there a "warranty fee" field?

It: Nothing matched that confidently. Your vault was last refreshed on 2026-05-20 — want to pull fresh metadata from the org (/sfi-refresh) in case it's new, or rephrase?

That is the headline behavior for resolution and routing: they never silently commit to a guess. Resolution is always heuristic and labeled as such. When several components are plausible it hands you a clarifying question; when nothing matches it offers to refresh from the org or stop. A high match score is string similarity, not proof. Source grep tools (sfi.search_apex_source, sfi.search_flow_metadata) walk the vaulted source/ tree from your last refresh — run /sfi-refresh before trusting an empty grep result.

Under the hood a semantic router (sfi.route_question) reads each question and returns a meaning-ranked shortlist of the sfi.* tools that can answer it — so your AI host picks and runs them without you ever typing a tool name. It runs fully offline (a small TF-IDF model over the tool catalog — no network, no embeddings service) and it advises rather than dictates: the host LLM sees the shortlist plus a short planner contract and decides which tools to run, in what order. The router also tags each question with the plane that answers it — the offline vault (metadata, dependencies, permissions), the live org (counts, samples, limits, inactive users — read-only, opt-in), or a hybrid of both (e.g. "is this field actually populated?"). Every answer is stamped with its provenance (offline_snapshot, live_org, or hybrid) and freshness. When nothing fits, it says so and logs the gap rather than guessing — so the library grows toward what people actually ask. (A deterministic, no-LLM routing mode is available via SFI_ROUTER_MODE=offline for CI / air-gapped hosts.)

How it works

One read-only refresh

... View full README on GitHub