Local AI Toolkit

OPEN SOURCE · WINDOWS · MCP

Lower costs.
Faster results.

Reduce paid cloud context with local search and analysis. Find relevant code in an index, inspect files on your machine, and send concise findings to your agent.

MIT licensed. Windows · MCP · CLI. Savings and latency depend on the task, index and hardware.

01Your repositorysource · symbols · worktrees
LOCAL AI
02CodeSearchsemantic + symbol search
03Shared brokerone model queue
04Evidence for your agentpaths · excerpts · provenance
01 / COST

Less cloud context

Let local tools read first and return relevant excerpts. Avoid paying to send unnecessary source text to the cloud.

02 / SPEED

Find the code sooner

Search an existing index by meaning or symbol, with source locations for the next step.

03 / CLARITY

See the trade-off

Usage notices distinguish estimated savings, additional overhead and unknown results.

INSIDE THE TOOLKIT

Follow the work.

Three views of one system. Select a stage to see its purpose and boundary.

Conceptual stages, not live status. The signing view includes a planned SignPath step.

Read the full architecture →

UNDERSTAND THE ESTIMATE

Less context.
Honest arithmetic.

Compare against the context necessary for the request, not the combined size of every file opened locally.

Read the methodology →

Illustrative only. All calculations stay in this page. No model call, analytics or account data.

3,200

S − V − 2R. The request is generated and later read as context. Local generation is not automatically credited. This is not a bill or measured savings.

THE HANDBOOK

A clear next step.

Start with a supported workflow, then go deeper.

FAQ

Before you begin.

Does local inference mean nothing reaches the cloud?

No. The calling client receives results and selected excerpts; a cloud agent may forward them to its provider. See the privacy policy for the exact boundary.

Does every call save tokens?

No. If the source is already in context, or the request and result cost more than the necessary alternative, delegation may add overhead. Missing evidence means an unknown estimate.

Are Windows binaries already Authenticode-signed?

Do not assume that. Current distribution uses an ECDSA-signed manifest. SignPath onboarding and a verified CI signing path must be completed before claiming an Authenticode-signed release.

Can several projects use Local AI together?

Yes. They share the broker and model queue. Check status and coordinate long operations; do not stop the shared runtime or unload another session's model to troubleshoot your own project.