A codebase graph can tell an agent that search.rs depends on store.rs, which files import a module, or where a symbol is defined. That helps when the current repository is the source of truth.
It does not answer a different kind of question: “What did the last agent learn while changing this area?”
That history may contain the failed command, rejected shortcut, user constraint, or review note that explains why the current code looks strange. Those details usually live in agent transcripts, not in the file graph.
Use ctx graph for repository shape
Codebase graph tools can answer questions such as:
- "Where is this symbol defined?"
- "Which files import this module?"
- "What depends on this package?"
- "How is this folder connected to the rest of the repo?"
ctx graph index . builds that map from a chosen project. Use ctx graph search, ctx graph callers, or ctx graph impact to follow its files, symbols, and relationships. Graph indexing is explicit; Graph settings explains updates and the saved database.
Use ctx search for prior work
ctx search starts from local agent history. It imports persisted provider sessions into a self-contained Tantivy Core and gives each session and event a ctx-owned identity. That lets an agent ask:
- "Who already investigated this failure mode?"
- "Which command showed the migration was incomplete?"
- "What did the previous agent try before changing this file?"
- "Where is the session that mentions this design decision?"
The repository may have changed since the session happened. That is useful context. An old command, error, or design note can explain why the current tree looks the way it does.
ctx returns results tied to sessions and events. A result can include a snippet, provider metadata, a ctx session ID, a ctx event ID, source information, and next commands for inspection:
ctx search "duplicate event ids"
ctx show event <ctx-event-id>
ctx show session <ctx-session-id>Working together
ctx graph and ctx history search are complementary. The graph can help find the right area of the repository. History search can recover what earlier agents learned while changing, testing, or debugging that area.
ctx keeps transcript content local: it reads local provider history, writes its own Tantivy Core index, and does not require model API calls, API keys, repository writes, or a hosted search service.