chat-js vs chatbot
Two of the top projects in Chat apps, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
chat-js
Next.js AI chat app scaffold with auth, branching and sharing
chatbot
Next.js chat template with Auth.js, Postgres history and AI Gateway models
Verdict
chat-js ranks higher, 72 to 66. Of the 4 score parts we measure for both, chat-js leads on 2, chatbot on 1 and 1 is even.
- Adoptionchatbot leads by 60 points, 91 to 31: a wide gap.
- FreshnessEven at 100.
- Maintenancechat-js leads by 52 points, 81 to 29: a wide gap.
- Agent-readychat-js leads by 85 points, 85 to 0: a wide gap.
Pick chat-js if you are
Developers building a Next.js AI chat product on Vercel and Postgres
- Scaffold CLI generates chat.config.ts and lists env vars for the chosen options
- Covers branching, public sharing, attachments, MCP and sandboxed code execution
Pick chatbot if you are
Teams starting a chat product on Next.js and Vercel
- Auth.js, Postgres chat history and Drizzle migrations wired out of the box
- Live demo plus a separate docs site
| What we compare | chat-js | chatbot |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 31, known | 91, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 81, healthy | 29, weak |
| Agent-ready | 85, ready | 0, none |
| Facts from GitHub and the README | ||
| Stars | 1.2k | 21k |
| License | Apache-2.0 (permissive) | Apache-2.0 (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Sep 2026 | None published |
| Language | TypeScript | TypeScript |
| Docker | No | No |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Not stated | Not stated |
chat-js
ChatJS is a Next.js chat application generated with `npx chat-js@alpha create`, which asks for gateway, feature and auth choices and writes a `chat.config.ts`. It uses the AI SDK with Vercel AI Gateway for 120+ models, Better Auth, Drizzle on PostgreSQL, and the EVE runtime for durable conversations and approvals. Chat features include attachments, branching, public sharing, web search, image generation, code execution and MCP.
Who it is for: Developers building a Next.js AI chat product on Vercel and Postgres
Strengths
- Scaffold CLI generates chat.config.ts and lists env vars for the chosen options
- Covers branching, public sharing, attachments, MCP and sandboxed code execution
- EVE runtime provides durable transcripts, approvals and stream recovery
- Optional Electron packaging for macOS, Windows and Linux desktop apps
Weaknesses
- CLI is alpha and its APIs are still changing; no stable 1.0 yet
- README says the EVE-only runtime is not yet established as production-ready
- Historical ChatJS conversations are not imported into the EVE runtime
- Built around Vercel AI Gateway and Blob; needs PostgreSQL and Node 24+
- TypeScript, Claude, GPT, Gemini, Grok
- Needs PostgreSQL, Vercel AI Gateway, Vercel Blob, EVE runtime, Node 24+, Bun
chatbot
Clone it and you get a Next.js App Router chat app on the AI SDK with Auth.js login, chat history in Neon Postgres through Drizzle migrations, file uploads to Vercel Blob and a streaming UI on shadcn/ui. Models route through Vercel AI Gateway; Mistral, Moonshot, DeepSeek, OpenAI and xAI are preconfigured in lib/ai/models.ts. For teams starting a chat product on Vercel who want auth and persistence wired on day one.
Who it is for: Teams starting a chat product on Next.js and Vercel
Strengths
- Auth.js, Postgres chat history and Drizzle migrations wired out of the box
- Live demo plus a separate docs site
- Per-model provider routing in lib/ai/models.ts; swapping vendors is a small edit
- Tests included
Weaknesses
- Defaults to Vercel services: AI Gateway, Neon Postgres, Vercel Blob
- Off Vercel you must set AI_GATEWAY_API_KEY and replace Blob storage
- No Docker or compose files
- TypeScript, ai-gateway, ai-sdk, openai, mistral
- Needs postgres, vercel-blob, ai-gateway-api-key
- GitHub template
- env example file
- sign-in: Auth.js
More in Chat apps
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.