JSPM

AI context layer for Claude Code, Cursor, Gemini CLI, and Antigravity — scans your web, backend, or mobile codebase once so AI understands your architecture, stack, and patterns without blind file hunting

Merlin - The Ultimate AI Brain for Claude Code, Codex, and other AI CLIs. One install: workflows, agents, loop, and Sights MCP server.

Interactive codebase intelligence CLI for JavaScript and TypeScript with browser dependency graphs, health dashboard, impact analysis, safe cleanup, CI checks, SARIF, reports, and AI-agent context.

Bounded conventions map and local-pattern discovery for AI coding agents. Local-first MCP server with AST-backed hybrid search.

An MCP server that gives Claude Code a curated atlas of your codebase — fusing LSP precision with architectural intent from your ADRs, docs, and git history.

Dependency intelligence for AI coding agents. Live CVE scanning, dependency health, upgrade planning, ecosystem news, decision memory — zero config, privacy-first. 9 tools standalone, 14 total with desktop app.

Ontology-powered project memory for AI coding assistants — your codebase as a knowledge graph

MCP server that gives AI agents (Claude, Cursor, Copilot) deep understanding of your codebase patterns, conventions, and architecture. Query patterns, security boundaries, call graphs in real-time.

Your codebase never forgets. Persistent, structured memory for AI coding agents.

Core library for Agent Input Compiler — deterministic context compilation pipeline and SQLite-backed storage

Agent Input Compiler — local-first MCP server for context compilation (Cursor, Claude Code, and other MCP clients)

Gives your AI coding assistant instant, accurate knowledge of every route, model, service, feature, and infrastructure element in your codebase.

Static code intelligence for AI-assisted development. Generates a dense CODEBASE.ctx from your source files — no API calls, pure local compute.

MCP server for Briefed - real-time codebase context that syncs as your team codes

Machine-readable codebase context for AI tools. The .dontreadme/ format is the open standard. This tool is the best generator.

Context-aware testing layer for Playwright MCP — scans your codebase, generates precise test plans, and produces CTO-level reports. Works with Claude Code and Cursor.

Auto-generate CLAUDE.md, .cursorrules, and copilot-instructions from your actual codebase. One command gives Claude Code, Cursor, and Copilot full project context.

Gives your AI coding assistant instant, accurate knowledge of every route, model, service, feature, and infrastructure element in your codebase.

MCP server that gives AI coding agents depxray codebase context, health scoring, dependency-chain explanations, cleanup suggestions, graph diffs, impact analysis, and refactor risk.