RepoGuard is a linter that checks codebases for architecture violations, aimed at code written with AI coding tools like Cursor and Claude. It enforces structural rules that AI-generated code often drifts from. Details are limited to the launch post and repository link.
Visit project ↗Oynix is a tool that gives coding agents awareness of the entire codebase locally, enabling more accurate and context-aware code assistance. It uses LLMs to understand and navigate the codebase, solving the problem of agents lacking full project context. Aimed at developers using AI coding assistants.
Oynix is a tool that gives coding agents awareness of the entire codebase locally, enabling more accurate and context-aware code assistance. It uses LLMs to understand and navigate the codebase, solving the problem of agents lacking full project context. Aimed at developers using AI coding assistants.
A constrained AI system designed solely to audit code for bugs, without attempting to fix them. It uses a custom architecture to force the LLM into a pure auditing role, tested on GitHub repos like Monica and Economizer, finding all known critical errors and some previously missed ones. Aimed at side project developers needing thorough code review.
A constrained AI system designed solely to audit code for bugs, without attempting to fix them. It uses a custom architecture to force the LLM into a pure auditing role, tested on GitHub repos like Monica and Economizer, finding all known critical errors and some previously missed ones. Aimed at side project developers needing thorough code review.
Tracelint is a new open-source linter that statically analyzes AI agent traces to catch errors without relying on an LLM judge. It provides deterministic checks for agent workflows, aiming to improve reliability and debuggability.
Tracelint is a new open-source linter that statically analyzes AI agent traces to catch errors without relying on an LLM judge. It provides deterministic checks for agent workflows, aiming to improve reliability and debuggability.
A set of rules for Claude Code that prevent AI coding agents from modifying or breaking existing working code. It solves the problem of AI agents accidentally introducing bugs or overwriting stable code, targeting developers using AI coding assistants.
A set of rules for Claude Code that prevent AI coding agents from modifying or breaking existing working code. It solves the problem of AI agents accidentally introducing bugs or overwriting stable code, targeting developers using AI coding assistants.
Viaduct provides architecture change sets, letting AI coding agents make structured, reviewable changes to a system's architecture. It targets developers using LLM coding agents who need controlled, explicit architectural modifications rather than ad-hoc code edits. How exactly LLMs are integrated is not detailed in the post excerpt.
Viaduct provides architecture change sets, letting AI coding agents make structured, reviewable changes to a system's architecture. It targets developers using LLM coding agents who need controlled, explicit architectural modifications rather than ad-hoc code edits. How exactly LLMs are integrated is not detailed in the post excerpt.