GraphHub

Run a direct Cypher query against the codebase graph database. Use this to find complex relationships.

Retrieve all symbols (classes, functions, etc.) defined in a specific file.

Search for code using natural language. Supports semantic (meaning-based), keyword, or hybrid search modes.

Search for symbols by their name. Supports exact or fuzzy matching.

Search for code and group results by file. Useful for understanding which files are most relevant.

Find symbols that are semantically similar to a given symbol. Useful for finding related code.

Explain how a search query will be processed. Shows tokenization and search strategy.

Get all callers and callees of a symbol by name. Shows the full call graph context around a function or class.

Analyze all symbols that directly call or import a given symbol. Shows what would break if the symbol changes.

Save a learning, decision, finding, or other observation to persistent memory. Searchable via recall with semantic similarity.

Search memory for past observations using natural language. Returns results ranked by semantic similarity.

View observations chronologically. Useful for reviewing what happened during a session or project.

Get statistics about stored observations: totals, counts by type, by project, by importance.

Get a specific observation by its ID.

Update an existing observation's content, title, importance, or tags.

Delete observations from memory. Can delete by ID, session, project, type, or date.

Get all observations that are linked to a specific code symbol.

One-shot debugging entry point. Given a bug description or error message, returns ranked candidate symbols enriched with callers, callees, and impact risk. Replaces the semantic_search → get_context → impact_analysis chain with a single call to save tokens.

Record a resolved bug so future agents can reuse the fix pattern. Stores symptom, root cause, and fix as a structured observation searchable via recall_bugfix.

Find past bug fixes with similar symptoms. Returns structured fix patterns (symptom/root_cause/fix) ranked by semantic similarity. Call this FIRST when debugging — a past fix may apply.

Cache which .skill.md / SKILL.md file was used for a task so similar future tasks route to the same skill without re-choosing. Record outcome to let recall_skill_choice rank successful choices higher.

Find which skill was used for similar past tasks. Skip the skill-selection decision for common task patterns.

Get definition + caller/callee counts for multiple symbols in one call. Replaces N get_context calls when an agent needs to look up several symbols at once. Default compact mode returns only counts; pass compact=false for full neighbor lists.

List the symbols in files changed by the current branch (or working tree / staged diff). Each entry includes a direct-caller count and risk bucket so agents know where breakage is most likely. Use this before committing or when reviewing a PR.

Find functions, methods, and classes that are never called by anything in the graph. Useful before refactors or cleanups. Common entry-point patterns (main, init, onX, handleX, etc.) are filtered out by default.

Find functions that are semantically similar to a given symbol — likely duplicate or near-duplicate implementations. Uses stored embeddings; no API cost.

Detect circular import chains or mutual-recursion call cycles in the codebase. Returns each cycle as an ordered list of file paths or symbol names.

Generate a structured pre-merge review of the current git diff. Returns each changed symbol with its blast radius, test coverage, and an overall risk rating (LOW/MEDIUM/HIGH/CRITICAL). Use this before committing or opening a PR.

Enforce architecture boundary rules — detect files that import across forbidden layer boundaries. Rules can be passed inline or loaded from .graphhub/arch-rules.json.

Show which functions and methods in the codebase are exercised by test files. Identifies uncovered symbols so agents know where to add tests.

Explore the inheritance and interface implementation tree for a class or interface. Returns ancestors (parent classes / implemented interfaces) and descendants (subclasses / implementors). Use before modifying a base class to understand the full blast radius across the hierarchy.

Surface TODO/FIXME/HACK/OPTIMIZE markers stored in the graph during indexing. Returns symbols sorted by risk score (debt_count × caller_count) so agents tackle the highest-impact debt first.