Lets users generate regex patterns from plain-English descriptions, then verifies them with Python's real re engine against generated positive and negative test strings, iterating on failures until they pass. It exposes this as a tool callable from MCP clients such as Claude Desktop or Claude Code.
Provides tools to test regex patterns for correctness, performance (ReDoS), and memory usage, and suggests safe rewrites. Enables LLMs to iterate on regex generation with verifiable feedback.
RegexForge gives AI agents a reliable way to get a regex without asking an LLM to hallucinate one. Pass in labeled examples (strings that should match, strings that shouldn't) plus an optional description; get back the regex, a proof matrix showing it handles every example, and a backtracking-risk audit flagging catastrophic-backtracking patterns. Pure symbolic synthesis over a template bank with
Enables LLM agents to extract, validate, and mask personally identifiable information using deterministic regular expressions, reducing token usage and hallucination risks.
Provides a tool to extract and validate regex patterns from text content, including flags, positions, and ReDoS risk assessment. Enables AI agents to identify potentially dangerous regular expressions in code or files without needing filesystem access.
Provides a suite of regex and text processing tools for AI agents, including pattern testing, extraction, and replacement with capture group support. It also enables various text transformations like case conversion, line sorting, and deduplication through the Model Context Protocol.
