AI agents burn tokens reading file dumps when a small snippet would do. Context fills up, they lose track, re-explore, read more. Round and round. CodeRay gives agents exact locations in your codebase instead of full files. They read only what they need, using ~70% fewer tokens on average. Three tools shipped over CLI and MCP: search (natural language), skeleton (structure and docs only), impact (what breaks before you change something). Runs fully local – your code never leaves your machine.
I built this after hitting token limits way more than expected on various subscription plans across different vendors.
The pattern was always the same: agent reads a whole file, it floods the context, it loses track, re-explores, reads more files. Round and round until the session dies.
CodeRay gives agents coordinates instead of content – file paths + line ranges. They locate first, then read only the lines that matter.
Most agents and coding tools already support reading files by line range but they just never get the chance to use it. CodeRay is the missing piece: it tells them where to look, so they read a 20-line slice instead of dumping a 2,000-line file into context. As a result, I got up to 70% token reduction consistently.
Works as a CLI or MCP stdio server – so agents can call it directly without leaving their workflow. Also ships with AGENTS.md and SKILLS.md: drop them in your repo and agents pick up the locate-first pattern automatically, no extra prompting needed.
Python (most tested), JS/TS (lighter tested) supported today, more coming.
No API key, no LLM, no network. Everything stays local – one gitignore-able artifact.
Additional features:
Multi-repo / monorepo – index multiple roots or just a subtree (sub-modules/files)
Hybrid search – combines semantic and keyword search under the hood for better results (vector + BM25 & RRF, with optional boosting)
Embedder runs fully on-device – CPU via fastembed, or faster on Apple Silicon via MLX
Live re-indexing – watches for file changes and updates incrementally; git-aware so it skips what it shouldn't touch; .coderay.toml controls what gets indexed.
No comment highlights available yet. Please check back later!
About CodeRay on Product Hunt
“Stop token burn. Agents read lines, not file dumps.”
CodeRay was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #163 on the daily leaderboard. AI agents burn tokens reading file dumps when a small snippet would do. Context fills up, they lose track, re-explore, read more. Round and round. CodeRay gives agents exact locations in your codebase instead of full files. They read only what they need, using ~70% fewer tokens on average. Three tools shipped over CLI and MCP: search (natural language), skeleton (structure and docs only), impact (what breaks before you change something). Runs fully local – your code never leaves your machine.
CodeRay was featured in Open Source (68.3k followers), Developer Tools (511k followers), Artificial Intelligence (466.2k followers) and GitHub (41.2k followers) on Product Hunt. Together, these topics include over 182.6k products, making this a competitive space to launch in.
Who hunted CodeRay?
CodeRay was hunted by Bogdan Copocean. 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 CodeRay stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Bogdan Copocean
Hi everyone,
I built this after hitting token limits way more than expected on various subscription plans across different vendors.
The pattern was always the same: agent reads a whole file, it floods the context, it loses track, re-explores, reads more files. Round and round until the session dies.
CodeRay gives agents coordinates instead of content – file paths + line ranges. They locate first, then read only the lines that matter.
Most agents and coding tools already support reading files by line range but they just never get the chance to use it. CodeRay is the missing piece: it tells them where to look, so they read a 20-line slice instead of dumping a 2,000-line file into context. As a result, I got up to 70% token reduction consistently.
Works as a CLI or MCP stdio server – so agents can call it directly without leaving their workflow. Also ships with AGENTS.md and SKILLS.md: drop them in your repo and agents pick up the locate-first pattern automatically, no extra prompting needed.
Python (most tested), JS/TS (lighter tested) supported today, more coming.
No API key, no LLM, no network. Everything stays local – one gitignore-able artifact.
Additional features:
Multi-repo / monorepo – index multiple roots or just a subtree (sub-modules/files)
Hybrid search – combines semantic and keyword search under the hood for better results (vector + BM25 & RRF, with optional boosting)
Embedder runs fully on-device – CPU via fastembed, or faster on Apple Silicon via MLX
Live re-indexing – watches for file changes and updates incrementally; git-aware so it skips what it shouldn't touch; .coderay.toml controls what gets indexed.
I'd love feedback on the tools themselves!