Compare AI tools

	Elicit S	GitNexus A	Replicate S	Flux (Black Forest Labs) A
Tagline	AI research assistant for academic literature.	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.	Run any open-source AI model with an API call.	Open weights + strong photorealism. The open-source answer.
Category	Research	Coding	Dev Platform	Image
Pricing	Free + $12-$42/mo	Free (MIT open source)	Pay per second of compute	API + open weights (Schnell is Apache 2.0)
Best for	Grad students, researchers, anyone doing literature reviews.	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.	Developers using open-source models (Flux, SDXL, Whisper, etc).	Developers + power users who want control and privacy.
Strengths	Searches 125M+ papers Extracts + synthesizes findings across papers Systematic review workflow	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	Tens of thousands of models (image, video, audio, LLMs) One-line API for any model Cog framework for custom model deploy	Runs locally on a beefy GPU Very photoreal Best open-weight model
Weaknesses	Academic-only Can hallucinate citations — verify everything	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	Cold starts on less-popular models Pricing gets real at scale	Harder to use than hosted tools Needs infra
Kai's verdict	S-tier for academic research. Nothing else comes close for systematic reviews.	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.)	S-tier for open-source model APIs. The default in this space.	A-tier. S-tier if you self-host. The reason open-source image gen matters.
Link	Open →	Open →	Open →	Open →