Launching today

Sverklo

Launching today

Local code intelligence for AI editors. No cloud.

1 follower

Local code intelligence for AI editors. No cloud.

1 follower

•

•

Sverklo is a local-first MCP server that gives AI coding assistants (Claude Code, Cursor, Windsurf) a symbol graph, hybrid search, and diff-aware PR review — without sending your code to anyone's cloud. MIT licensed, single SQLite file, 20 tools over MCP.

Free

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team / Built With

AppSignal — Track your app’s health, errors and performance with ease

Track your app’s health, errors and performance with ease

Promoted

Maker

📌

Hey PH! I'm the maker of Sverklo. I built this because every AI coding tool I tried either sent my code to the cloud or gave me keyword search that missed the actual symbols I needed. So I built a local MCP server that combines BM25 lexical search + ONNX vector embeddings + PageRank over the dependency graph — all running on your machine, all stored in a single SQLite file. The thing I'm most proud of: I dogfooded it on its own codebase before shipping. Ran 3 structured sessions where I used Sverklo to navigate and refactor Sverklo's own code. Found 4 real bugs in my own tool that unit tests missed: 1. Impact analysis silently dropped repeat call sites 2. Reference search returned 48 substring matches drowning 5 real hits 3. Lookup returned "No results" on valid queries (silent failure) 4. Parser had an off-by-one skipping functions after the first in multi-function files All four are fixed, regression-tested, and documented in the full unedited session log: github.com/nickshanks347/sverklo/blob/main/DOGFOOD.md I'd love your honest feedback — especially if you try it on a real codebase and something feels wrong. I triage issues within hours. npm install -g sverklo && cd your-project && sverklo init

Report

11h ago

Forum Threads

p/sverklo

•

10h ago

I dogfooded my own code intelligence tool and found 4 bugs I'd shipped

Building Sverklo (launching tomorrow on PH), I ran a structured dogfood protocol used the tool on its own codebase to find real bugs before users did.

Found 4 integration-level bugs that unit tests missed:

Impact analysis silently dropped repeat call sites the worst possible failure for a refactor-safety
Reference search returned 48 substring matches, drowning the 5 real
Lookup returned "No results" on valid queries instead of explaining why
Parser off-by-one skipped every function after the first in multi-function
All fixed, regression-tested, and documented in a full unedited session log

View all