Plug your AI agents into any provider

             

What is Manifest?

Manifest is an open-source model router for AI agents and apps. Connect your API keys, subscriptions, and local models to one OpenAI-compatible endpoint, and each query goes to the right model. No single-provider lock-in.

• 🔀 Routing based on complexity, specificity and custom HTTP headers
• 🎛️ Mix your providers: API keys, Subscriptions, Local models, Custom providers
• 📊 Track every single dollar, setup notifications and limits
• 🚑 Fallback on different models when queries fails

Quick start

Cloud version

Go to app.manifest.build and follow the guide.

Self-hosted

Manifest ships as a Docker image. One command:

bash <(curl -sSL https://raw.githubusercontent.com/mnfst/manifest/main/docker/install.sh)

Open http://localhost:2099 and sign up — the first account you create becomes the admin. Full self-hosting guide: docker/DOCKER_README.md.

Deploy with one click

Platform	Notes
Railway	Best path. Template includes Manifest and PostgreSQL.
Render	Blueprint includes Manifest and Render PostgreSQL.
DigitalOcean	App Platform button includes Manifest and a Dev PostgreSQL database.
AWS	CloudFormation quick-create for ECS, RDS, and Secrets Manager.
GCP	Cloud Shell guided deploy for Cloud Run, Cloud SQL, and Secret Manager.

Full deployment guides: Railway, Render, DigitalOcean, AWS, GCP, Fly.io, Coolify, Easypanel, Heroku, and Koyeb.

The old npm-based self-hosting path is no longer supported. Use the Docker image or one of the deployment guides above.

Providers

Manifest connects to 300+ models through 31 built-in provider connections plus any custom OpenAI/Anthropic-compatible endpoint. Bring your own API key, reuse one of 18 subscription flows, or run models locally. Everything is routed through the same /auto endpoint.

Provider catalogs are discovered dynamically when credentials are connected. The examples below are representative, not exhaustive.

Provider	API key / local	Subscription	Model catalog
OpenAI	✅	✅ ChatGPT Plus / Pro / Team	GPT-5 family, o-series, Codex / Responses models
Anthropic	✅	✅ Claude Max / Pro	Claude Opus, Sonnet, Haiku, Fable
Google	✅	✅ Sign in with Google	Gemini 3.1, Gemini 3, Gemini 2.5
xAI	✅	✅ Grok subscription	Grok, Grok Code Fast
AWS Bedrock	✅	—	Claude, Llama, Mistral, Nova via Bedrock
Alibaba Cloud / Qwen	✅	✅ Qwen Token Plan	Qwen, DeepSeek, Kimi, GLM via Alibaba Cloud
DeepSeek	✅	—	DeepSeek V3, DeepSeek R1
Mistral	✅	✅ Mistral Vibe	Mistral Large, Codestral, Pixtral
Moonshot (Kimi)	✅	✅ Kimi Coding Plan	Kimi K2, Kimi for Coding, Moonshot v1
MiniMax	✅	✅ MiniMax Coding Plan	MiniMax M3, M2.7, M2.5
Xiaomi MiMo	✅	✅ MiMo Token Plan	MiMo V2.5 Pro, V2.5, Flash
Z.ai	✅	✅ GLM Coding Plan	GLM 5.2, GLM 5.1, GLM 5 Turbo
BytePlus	—	✅ ModelArk Coding Plan	Ark Code, Seed Code, GLM, Kimi, DeepSeek
GitHub Copilot	—	✅ Copilot subscription	Claude, GPT, Gemini, Grok via Copilot
Kiro	—	✅ Kiro subscription	kiro/auto, Claude, DeepSeek, MiniMax, GLM, Qwen
Command Code	—	✅ Command Code subscription	Claude, GPT, Kimi, DeepSeek, Qwen
ClinePass	—	✅ ClinePass subscription	cline-pass/glm-5.2, Kimi, DeepSeek, MiMo, MiniMax, Qwen
NousResearch	—	✅ NousResearch subscription	NousResearch Portal model catalog
OpenCode Go	—	✅ OpenCode Go	GLM, Kimi, MiMo, MiniMax
Ollama / Ollama Cloud	🖥️ Local	✅ Ollama Cloud	Local or cloud tags: Llama, Qwen, DeepSeek, Gemma
LM Studio	🖥️ Local	—	Local GGUF models, port 1234
llama.cpp	🖥️ Local	—	Local GGUF models, port 8080
OpenRouter	✅	—	300+ models across labs
OpenCode Zen	✅	—	Claude, GPT, Gemini, Qwen, GLM, MiniMax
Kilo	✅	—	Kilo Gateway catalog
Cerebras	✅	—	GPT OSS, GLM on Cerebras inference
Fireworks AI	✅	—	GLM 5.2, DeepSeek, Kimi, Qwen, Llama
Groq	✅	—	Llama, Gemma, Mixtral
NVIDIA NIM	✅	—	Nemotron, Llama, Mistral
Pioneer	✅	—	OpenAI-compatible and fine-tuned Pioneer models
Custom	✅	—	Any /v1/chat/completions or /v1/messages endpoint

Quick links

• Docs
• Discord
• Discussions
• Contributing
• GitHub

License

MIT