Detect missing
engineering controls.
Review tests, implementation integrity and missing verification evidence in the context of your project.
CODEBASE INTELLIGENCE, ON YOUR MACHINE
Build a local graph of files, symbols and dependencies. Retrieve source-backed context, investigate failures and verify changes from your terminal or coding assistant.
Workflow illustration · results depend on repository evidence
Bring the context to your coding assistant.
Explore selected skills and generic clients →BEFORE YOU CHANGE THE CODE
A shared source graph connects what you read, what you change, and what you check next.
Review tests, implementation integrity and missing verification evidence in the context of your project.
Follow working-tree files into reverse dependencies and related tests. Inspect recommended checks before approving execution.
These diagrams explain the workflow. Findings support review; they do not guarantee correctness.
EXPLORE THE FEATURES
Browse ten feature groups with commands, examples and the limits of each analysis.
Explore files, symbols, imports and call relationships with clickable source evidence.
Explore capability →Select relevant source and optional workflow skills under a shared context budget.
Explore capability →Explore architecture views and compare dependencies with explicit rules and detected conventions.
Explore capability →Inspect working-tree impact, discover checks and record approved execution in the guardrail ledger.
Explore capability →Inspect tests, supplied coverage, dependencies, implementation integrity and static HTML delivery signals.
Explore capability →Inventory prompts, examine evidence and compare candidates using supplied cases and recorded outputs.
Explore capability →Search Git changes and inspect the evidence behind engineering concepts used in a repository.
Explore capability →Connect error output and source locations to tentative hypotheses and targeted diagnostic actions.
Explore capability →Inspect static data-flow traces, trust-boundary signals and configuration concerns with source references.
Explore capability →Route and install selected catalog skills, including detailed Superpowers planning, TDD and debugging.
Explore capability →LOCAL DASHBOARD
Every view is served locally from the project you scan. Open a screenshot to see the dashboard at full size.









INSTALL LOCALLY
Install FEHM from PyPI with uv, scan your repository, and select useful workflows. Ordinary retrieval and skill routing run locally without an LLM.
Follow the installation guide →$ fehm scan .
$ fehm search "authentication"
$ fehm serve --port 4317
BEFORE YOU START
Install FEHM from PyPI with uv tool install fehm. It includes the engine and uses a private Node runtime dependency. No source checkout is needed; npm publication is pending.
Ordinary graph queries run locally and return evidence. Your coding assistant can use that evidence to explain the code. Optional external summary and reranker commands may use a provider when configured and invoked.
TypeScript and JavaScript have the deepest analysis. Python, Go, Rust, and Java have shallower declaration, import, and call resolution.
Follow the setup guide, scan a repository you know, and ask about a familiar flow. Then connect your coding assistant to reuse that context.
SCAN · QUERY · REVIEW