This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
GitHub
In-memory code knowledge graph and MCP server for AI agents
PigeonGraph stops coding agents from wasting 20+ turns on grep loops. It builds an in-memory knowledge graph locally with Node 24 SQLite WAL, connecting AST symbols and dynamic runtime routes for Claude, Cursor, and Gemini in a single turn. 100% local, MIT licensed
I built PigeonGraph because I was spending too many tokens watching Claude Code and Cursor loop through grep searches on medium-sized repositories.
I tried existing code graph projects, but they either required cloud services, missed runtime route handlers, or dumped too much raw text back into the prompt.
PigeonGraph is completely local, runs in Node 24 with native SQLite WAL, and exposes an MCP server that gives agents exact call chains and route links in one turn.
It is 100% free, open source under the MIT license, and easy to run. I would love your feedback, stars, and contributions on GitHub.
About GitHub on Product Hunt
“In-memory code knowledge graph and MCP server for AI agents”
GitHub was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #112 on the daily leaderboard. PigeonGraph stops coding agents from wasting 20+ turns on grep loops. It builds an in-memory knowledge graph locally with Node 24 SQLite WAL, connecting AST symbols and dynamic runtime routes for Claude, Cursor, and Gemini in a single turn. 100% local, MIT licensed
On the analytics side, GitHub competes within Developer Tools, GitHub and Tech — topics that collectively have 1.2M followers on Product Hunt. The dashboard above tracks how GitHub performed against the three products that launched closest to it on the same day.
Who hunted GitHub?
GitHub was hunted by Hoppy Beast. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of GitHub including community comment highlights and product details, visit the product overview.
Hoppy Beast