Compare AI tools

	Claude Agent SDK S	Runway S	NotebookLM S	GitNexus A
Tagline	Anthropic's SDK for building your own agents on Claude.	The pro's AI video tool. Gen-4 is the current bar.	Google's research notebook. Turns your docs into a podcast.	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	Agents	Video	Research	Coding
Pricing	API usage + SDK is free	Free + $15-$95/mo	Free	Free (MIT open source)
Best for	Developers building custom agents for their own company/product.	Marketing video, pitch decks, b-roll, creative shorts.	Students, researchers, anyone with a stack of PDFs or a topic to learn.	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	Production-grade agent primitives Built on Claude (best reasoning) Full control — build exactly what you need	Most mature video workflow Character consistency via Act-One Gen-4 quality is production-grade	Upload anything, ask questions, get cited answers Audio Overview turns docs into a 10-min podcast Great for studying	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	Developer-only You build the UI	Expensive at scale Still needs post-editing	Google-only Can be slow on large corpora	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 builders. The right primitives. What Kai is built on under the hood.	S-tier. Market leader with reason. Start here for serious video.	S-tier for study. The Audio Overview is a killer feature. Try it with three of your favorite PDFs.	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 →