Reference vs sizeless: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of Reference and sizeless — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
R
Reference
Rahul Thennarasu
Local, offline semantic search for your files and code — built for AI agents like Claude Code, with an MCP server.
Key features
- Local Semantic Index: Runs a local embedding model over your files and code so nothing leaves your machine.
- Live Auto-Reindexing: Updates the index as you save files, keeping search results current with the code you are actively writing.
- Code-Aware Chunking: Uses tree-sitter to chunk on functions and syntactic units, so results are cited down to the exact code region.
- Built-in MCP Server: Exposes /search, /explain, /find_similar and /check_doc_drift endpoints so Claude Code and other agents can query directly.
- Cited Answers: Every result points back to a file and function, replacing generic AI advice with grounded, verifiable references.
- Doc Drift Checks: /check_doc_drift flags places where documentation has fallen out of sync with the underlying code.
- Cross-Codebase Similarity: /find_similar surfaces analogous implementations elsewhere in the codebase for reuse and refactoring.
Best for
- Grounded Coding Q&A: Ask 'how did I implement rate limiting here' and get the actual function back, not a generic explanation.
- Claude Code Context Injection: Use the MCP server so Claude Code pulls precise cited snippets instead of running expensive grep loops.
- Refactoring Prep: Use /find_similar to locate analogous implementations across the repo before consolidating or standardizing them.
- Doc-Code Alignment: Run /check_doc_drift to catch documentation that no longer matches the code it describes.
- Offline / Air-Gapped Work: Semantic code search on machines that can't upload source to cloud embedding services.
- Cross-Project Recall: Reindex multiple repos locally to find prior solutions you already wrote in another project.
sizeless
sizeless
Turns a smartphone video of an open trench into a centimetre-accurate 3D point cloud, CAD as-built plan and GIS-ready digital twin of buried utilities.
Key features
- Smartphone capture: Field crews record an open trench with a standard iPhone Pro — no specialist scanning hardware and no separate surveying appointment
- Centimetre-accurate point clouds: Reconstruction algorithms developed at ETH Zurich build a high-resolution 3D point cloud of the excavation from the video alone
- Standards-compliant CAD output: Generates as-built plans in DWG and DXF, with couplings and pipe runs identified and measurements simplified
- 3D digital twin and GIS export: Produces a model of the pipe route including building entries that drops into existing GIS systems
- Works without GPS: Captures basement sections and building entry points where GNSS-based surveying fails
- Immediate backfilling: Because capture takes minutes, trenches close right after filming instead of waiting on a survey crew
- Documentation in about 72 hours: Complete records arrive weeks earlier than conventional surveying, enabling prompt connection billing
- Third-party utility capture: Records crossing utilities and as-laid geometry as unbroken 3D evidence, replacing hand sketches
Best for
- A utility network operator documenting residential service connections without booking a surveyor for every site
- A contractor closing a trench the same day instead of leaving it open pending a survey appointment
- Capturing a building entry point in a basement where GPS-based surveying cannot get a fix
- A district heating project producing as-built DWG plans for regulatory sign-off
- Spotting a laying error in the 3D point cloud before backfilling, while the fix is still cheap
- Feeding as-built pipe geometry into a GIS system for long-term network maintenance planning