Fehm 1.0.0 Release notes ↗

CODEBASE INTELLIGENCE, ON YOUR MACHINE

Codebase context
for your
AI assistant.

Build a local graph of files, symbols and dependencies. Retrieve source-backed context, investigate failures and verify changes from your terminal or coding assistant.

Local processingOpen sourceNo account
THE CONTEXT WORKFLOW↗
› add refunds your task
{ }
Relevant sourceSymbols, excerpts & locations
↗
⌁
Connected evidenceRelationships, tests & architecture
↗
≡
Selected guidanceOptional workflow skills
↗
FEHM CONTEXTSource context within your budget.Ranked evidence for your assistant
$ fehm context "add refunds"

Workflow illustration · results depend on repository evidence

Bring the context to your coding assistant.

Claude CodeCursorCodexGemini CLICopilot CLIVS Code
Explore selected skills and generic clients →

BEFORE YOU CHANGE THE CODE

Check the boundaries.
Inspect the impact.

A shared source graph connects what you read, what you change, and what you check next.

ENGINEERING READINESS

Detect missing
engineering controls.

Review tests, implementation integrity and missing verification evidence in the context of your project.

Explore architecture & drift ↗
CHANGE VERIFICATION

Find the code
a change can affect.

Follow working-tree files into reverse dependencies and related tests. Inspect recommended checks before approving execution.

Explore change verification ↗

These diagrams explain the workflow. Findings support review; they do not guarantee correctness.

EXPLORE THE FEATURES

Explore code.
Review changes.

Browse ten feature groups with commands, examples and the limits of each analysis.

LOCAL DASHBOARD

See the evidence.
Follow the graph.

Every view is served locally from the project you scan. Open a screenshot to see the dashboard at full size.

Codebase graph in the FEHM local dashboard
Codebase graphExplore files, symbols, folders and relationships in one visual graph.
Explain codebase in the FEHM local dashboard
Explain codebaseRead a source-linked briefing for an unfamiliar repository.
Architecture in the FEHM local dashboard
ArchitectureInspect system structure, components and dependency views.
Architecture data flow in the FEHM local dashboard
Architecture data flowTrace how data moves through the architecture.
Architecture drift in the FEHM local dashboard
Architecture driftReview structural signals against project conventions.
Security review in the FEHM local dashboard
Security reviewTrace static security signals and trust boundaries.
Project health in the FEHM local dashboard
Project healthReview tests, dependencies, quality and readiness evidence.
Prompt intelligence in the FEHM local dashboard
Prompt intelligenceInventory prompts, contracts and evaluation evidence.
Engineering concepts in the FEHM local dashboard
Engineering conceptsSearch concepts and the evidence that supports them.

INSTALL LOCALLY

It starts in
your repository.

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 →
~/your-projectTERMINAL

$ fehm scan .

$ fehm search "authentication"

$ fehm serve --port 4317

CLI · library · localhost dashboard
What’s included in Fehm ↗

BEFORE YOU START

Installation,
privacy and languages.

How do I install FEHM?

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.

Does a query call an AI model?

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.

Which languages can I analyze?

TypeScript and JavaScript have the deepest analysis. Python, Go, Rust, and Java have shallower declaration, import, and call resolution.

Where should I start?

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

Start with your repository.

Start with Fehm ↗