Compare AI tools

	Elicit S	Sora A	GitNexus A
Tagline	AI research assistant for academic literature.	OpenAI's video model. Long clips, cinematic quality.	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	Video	Coding
Pricing	Free + $12-$42/mo	Included with ChatGPT Plus/Pro	Free (MIT open source)
Best for	Grad students, researchers, anyone doing literature reviews.	ChatGPT subscribers experimenting with cinematic shots.	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	Searches 125M+ papers Extracts + synthesizes findings across papers Systematic review workflow	Up to 20-sec clips at 1080p Strong physics + scene composition Storyboard feature for longer narratives Remix existing videos	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	Academic-only Can hallucinate citations — verify everything	Stricter content policy than competitors Hit-or-miss on complex motion Text-in-video still struggles	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 academic research. Nothing else comes close for systematic reviews.	A-tier. Amazing when it works, frustrating when it doesn't. Runway still more reliable for pros.	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 →