Compare AI tools

	Perplexity S	OpenRouter S	Galileo AI B	GitNexus A
Tagline	AI search done right. Cited answers, not chat theater.	One API, every model. Pay-as-you-go, no subscriptions.	Prompt to UI design. Figma-ready outputs.	An open-source, MCP-native knowledge graph engine that gives AI coding agents (Cursor, Claude Code, Windsurf) genuine structural awareness of your codebase before they touch a single line.
Category	Research	Dev Platform	Design	Coding
Pricing	Free + $20/mo Pro	Pay per token — model-dependent	Free trial + paid plans	Free (MIT open source)
Best for	Replacing Google for any question where you want a cited answer in seconds.	Developers experimenting across models. Apps that want fallback logic.	Designers brainstorming first drafts.	Developers working in large or unfamiliar codebases who want their AI coding agent to stop making confident, structurally blind edits — especially Claude Code power users.
Strengths	Sources every claim Fast, current answers Pro Search runs multi-step research Spaces for persistent context	300+ models from one endpoint Automatic fallbacks between providers No subscription — just pay what you use	Prompt-to-UI with real layouts Exports to Figma Faster than hand-designing from scratch	Pre-computes a full dependency graph (functions, imports, class inheritance, execution flows) via Tree-sitter ASTs — agents query structure, they don't guess at it Zero-server, privacy-first: CLI runs entirely locally with no network calls; browser UI processes code client-side and never uploads it Deepest Claude Code integration on the market: MCP tools + agent skills + PreToolUse/PostToolUse hooks that auto-enrich searches and auto-reindex after commits One global MCP server handles multiple indexed repos — set up once with npx gitnexus setup and forget it detect_impact and generate_map MCP prompts give pre-commit blast-radius analysis and auto-generated Mermaid architecture docs
Weaknesses	Not a general chatbot Answers can be shallow on complex topics	Slight markup over direct API Some provider features not exposed	Output needs designer polish Pricing unclear / changes often	Browser-side RAG has hard ceilings: WASM heap limits constrain embedding model quality compared to server-side tools; monorepos or repos >50k files hit practical walls Community-built and not officially maintained — velocity and long-term support depend on contributor goodwill Claude Code gets the full integration experience; other editors (Windsurf, Cursor) get progressively less — value is uneven depending on your editor
Kai's verdict	S-tier for search. I use it before Google now. If you're still Googling everything, try this for a week.	S-tier for model-shopping. I use this for every prototype before committing.	B-tier. Useful for first drafts. v0 is the better bet for shipping code.	GitNexus solves a real and underappreciated problem: AI coding agents are syntactically fluent but architecturally blind, and plugging a pre-computed knowledge graph into the MCP layer is the right fix. 28k GitHub stars in days suggests the pain is widely felt — just go in knowing it's a community project, not a polished product. (Verdict pending Phi's full review.)
Link	Open →	Open →	Open →	Open →