Short answer: Brigade ships a built-in code graph, formerly the standalone GraphTrail: a local SQLite code graph over the CLI and an optional MCP server. Brigade attaches code-graph deltas to verify and run receipts when the graph is present. Everything stays on disk; nothing is required for Brigade to work without it.
The problem
Agents reason about code from whatever fits in context. Grep finds strings. It does not answer “who calls this?” or “what broke when this symbol changed?” Hosted code-intel tools help, but they move your tree off-machine and do not plug into a local receipt loop.
The path
brigade setup # installs the code-graph engine, digest-verified
brigade code sync # builds .graphtrail/graphtrail.db in the repo
brigade code context "auth middleware" --markdown
brigade search doctor # advisory code-graph + optional code-search health
brigade work verify run --target . --command "pytest -q" --capture brigade-work
The code graph owns the structure. Brigade owns the operator loop: when a graph is present, verify and run receipts can carry a compact code_graph_delta so the next session sees what actually changed.
Brigade surface
The code graph ships with brigade setup, and brigade code sync / context / impact are the branded query surface. A compatibility path also wires it through the search station:
brigade add searchorbrigade add graphtrail(compatibility shims afterbrigade setup)brigade search status/doctor/sync plan(plans only; does not run sync for you)
Optional semantic search (code-search-api / MCP) is a sibling, not a replacement for the graph.
When this is enough
Use Brigade’s code graph when you want local callers/callees/impact and structural proof on verify receipts. Use a full language server or hosted code-intel product when you need deep IDE features, multi-language enterprise indexes, or team-wide cloud search.
Questions
Does Brigade require a code graph? No. The code graph is optional and fail-open. Absent tools never break a workspace doctor run.
Is the graph uploaded anywhere? No. The database lives under .graphtrail/ in the target repo.
Can agents query it over MCP? Yes. The code graph ships a read-only MCP surface; Brigade can also sync MCP catalogs with brigade mcp sync.
Capability page: Code Intelligence on brigade.tools. CLI: command docs.