Ross ROSS = Recommend OSS · open-source software intelligence for agents

coaidev/coai

🚀 Next Gen Multi-tenant AI One-Stop Solution. Builtin Admin & Billing System. Enterprise-Grade Unified LLM Gateway Support for 200+ Models And 35+ Providers, Load Balacing w/ Priority-base Routing, Cost Management, Chat Share, Cloud Sync, Credit/Subscription Billing, All File Parsing, Web Search, Built-in Model Cache. observed · 2026-08-28

github.com/coaidev/coai · homepage · TypeScript · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

56/100

  • Activity 71
  • Release rhythm 21
  • Longevity 81
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 276
  • age_days: 1143
  • days_rel: 314
  • days_push: 174
  • n_releases_24m: 2

Full methodology

Adoption not part of the score

9295 stars · 1220 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

CoAI.Dev is a self-hostable, multi-tenant AI platform combining a ChatGPT-style chat UI with an enterprise-grade unified LLM gateway supporting 200+ models across 35+ providers. It includes load balancing with priority-based routing, cost management, credit/subscription billing, file parsing, web search, model caching, and an admin dashboard.

Use cases

  • self-host a chatgpt-like ai assistant with multi-model support
  • unified llm gateway proxying openai anthropic gemini and other providers
  • manage api keys and load balance across multiple llm providers with failover
  • sell ai chat subscriptions with credit and token-based billing
  • chat with pdf and office documents using llm file parsing
  • share chat conversations via links and sync across devices
  • track llm usage costs and analytics per user or tenant
  • add web search to llm chat responses

When to choose

  • you need an all-in-one self-hosted platform combining chat UI, gateway, and billing
  • you want to route requests across many LLM providers with priority and load balancing
  • you run a multi-tenant AI service and need quotas, credits, and subscription billing
  • you want built-in file parsing, OCR, and web search in a chat assistant

When to avoid

  • you only need a lightweight API proxy without chat UI or billing
  • you want a minimal single-user chat client without admin overhead
  • you need a fully managed SaaS rather than self-hosting
  • your stack requires a runtime other than Docker/Kubernetes deployments

Facets

application · maturity active

llm-inference chatbot rag api-gateway file-upload image-processing ocr caching load-testing analytics monitoring auth internationalization speech-recognition stable-diffusion large-language-models chatbots self-hosted web-development artificial-intelligence developer-tools apis self-hosted cross-platform go llm-gateway multi-tenant ai-gateway billing-system chat-ui model-routing one-api-alternative chatgpt-ui admin-dashboard subscription-billing billing web-search docker web-server nodejs typescript

4 sources

Member repositories

RepositoryRoleHealth v2
coaidev/coaimain56

For agents

markdown · JSON · MCP: product_card(name="coaidev/coai")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem