scalps

The company appears to be a solo developer project named scalps, which self-reports as a local C++ definition-search tool built with Codex GPT-5.6 ("Sol") in approximately three days. The author states that it is designed to solve a specific problem: finding the right function in a large codebase when the user knows what it does but not its exact name.

The project was submitted to the OpenAI 2026 hackathon and is described as a novel approach using Clang for extraction, SQLite for indexing, and deterministic ranking. It claims to return complete definitions rather than arbitrary source chunks, with explainable results.

What changed: The author reports building this tool in a short timeframe using AI assistance, with no evidence of prior development or commercial traction.

The single most important open question: Is there any indication that the tool has been adopted by developers beyond the author's own use case? There is no evidence of customers, revenue, or usage metrics.

• The description states that scalps is a local C++ definition-search tool.
• It uses Clang to identify function and method definitions in C++ codebases.
• It stores metadata including names, signatures, comments, bodies, source ranges, and compiler-resolved relationships.
• It retrieves candidates using literal, identifier, and field-aware lexical search, then ranks them with deterministic structural evidence.
• The tool returns exact source locations and context, not arbitrary code snippets.
• It is built in C++, and uses SQLite for indexing.
• It supports both concise default output and detailed verbose output.

Note: This is a self-reported technical description. No independent verification or demonstration of the tool exists beyond the author's account.

• The author states that scalps was built to address a common but costly developer failure: finding functions in large codebases when the user knows what it does, but not its exact name.
• It is positioned as a definition-first architecture, distinct from general-purpose search tools like grepai or cocoindex-code.
• The tool is described as specifically for C++, avoiding broad natural-language code search systems.
• The author claims that Sol (Codex GPT-5.6) was used to propose the architecture and implement it, with human oversight.
• It is presented as a novel solution in an area where permissively licensed tools are sparse.

Inference: The positioning implies a niche within developer tooling, focused on improving code navigation for C++ developers. However, this is not validated by any external data or market feedback.

• The description states that scalps is intended for developers working with large C++ codebases.
• It targets users who know what a function does but do not know its exact name.
• It is described as a tool for local, deterministic, explainable, and narrowly focused use cases.

Note: No evidence of specific customer segments or personas is provided. The ICP is inferred from the stated problem and technical focus.

• There is no evidence in the description of any business model or pricing structure.
• The tool is described as a local, open-source project, with no mention of monetization or commercial use cases.

Inference: If this is intended for commercial use, it is not evident from the self-reported account. No pricing, licensing, or revenue streams are mentioned.

• The tool was built in C++ using Clang, SQLite, and Codex GPT-5.6 ("Sol").
• It implements a definition-first architecture with Clang extraction pipeline, versioned SQLite index, incremental updates, explainable ranking, definition context, JSON output, packaging, tests, and documentation.
• Development was conducted through 54 Zed sessions, each with reviewable commits.
• Each commit was reviewed by Grok 4.5, and findings were corrected and verified via test suite.
• The human made key decisions, including the definition-context feature, output formats, and local-only constraint.

Note: These are self-reported technical details. No evidence of external validation or production use is provided.

• The project was submitted to the OpenAI 2026 hackathon.
• It was built in approximately three days, with a staged roadmap and reviewed commits.
• The author states that it is a novel solution, but does not provide evidence of adoption or usage beyond the author’s own use case.

Inference: No traction, revenue, or customer data is evident. The project appears to be in early-stage development or prototype form.

• The description mentions that tools like grepai and cocoindex-code failed to locate relevant C++ functions.
• It claims that the proposed architecture is “unusually specific” in the current ecosystem.
• It is positioned as a narrowly focused tool, not a general-purpose code search system.

Note: No mention of direct competitors or market positioning beyond the stated problem. No competitive analysis or market size data is provided.

• The project is described as a single-developer hackathon submission with no evidence of prior traction or commercialization.
• It is not independently verified, and no third-party validation or user feedback is included.
• The tool is local-only, which may limit its appeal in enterprise environments where centralized tools are preferred.
• There is no indication of scalability, performance testing, or integration with existing IDEs.
• The tool is built using AI-assisted development, but no evidence exists that this approach has been validated at scale.

Inference: The lack of any commercial or user data raises questions about viability and market readiness.

1. What specific use cases have you tested the tool with, and how did it perform?
2. Have you shared this tool with other developers for feedback or adoption?
3. Is there a plan to expand beyond C++ or make the tool available in non-local environments?
4. How do you envision monetizing or scaling this tool if at all?
5. What are the limitations of the current implementation that would need to be addressed before broader use?