Reference is local semantic search for your files and code, built for AI agents. No cloud, nothing leaves your machine. Ask it "how did I implement rate limiting here" and get your actual code back, cited down to the exact function, not generic advice. Live index that updates as you save, code-aware chunking (tree-sitter), and a built-in MCP server (/search, /explain, /find_similar, /check_doc_drift)so Claude Code gets precise cited results instead of burning tokens on grep loops.
Built this after burning tokens and context for every new Claude thread I open. An embedding model uses a fraction of the memory a local LLM does, and gives me back what I (or Claude) are looking for instantly. It's local, offline, and now Claude can just ask the index directly. Would love to hear what you think!
Local + cited-to-the-exact-function is the right combo. Which embedding model runs locally, and how large can an indexed codebase get before search latency starts to hurt?
About Reference on Product Hunt
“Local semantic search for AI agents”
Reference launched on Product Hunt on August 7th, 2026 and earned 83 upvotes and 3 comments, placing #20 on the daily leaderboard. Reference is local semantic search for your files and code, built for AI agents. No cloud, nothing leaves your machine. Ask it "how did I implement rate limiting here" and get your actual code back, cited down to the exact function, not generic advice. Live index that updates as you save, code-aware chunking (tree-sitter), and a built-in MCP server (/search, /explain, /find_similar, /check_doc_drift)so Claude Code gets precise cited results instead of burning tokens on grep loops.
Reference was featured in Mac (103.6k followers), Developer Tools (517.2k followers), Artificial Intelligence (475.5k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 226.6k products, making this a competitive space to launch in.
Who hunted Reference?
Reference was hunted by Rahul Thennarasu. 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.
Want to see how Reference stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Rahul Thennarasu
Built this after burning tokens and context for every new Claude thread I open. An embedding model uses a fraction of the memory a local LLM does, and gives me back what I (or Claude) are looking for instantly. It's local, offline, and now Claude can just ask the index directly. Would love to hear what you think!