Star ๅކๅฒ่ถ‹ๅŠฟ
ๆ•ฐๆฎๆฅๆบ: GitHub API ยท ็”Ÿๆˆ่‡ช Stargazers.cn
README.md

Manifest

AI Agents that don't break

manifest-gh

Deploy on Render Deploy on Railway Deploy on AWS Deploy on GCP

GitHub stars ย  Docker pulls ย  Docker image size ย  CI status ย  Codecov ย  license ย  Discord

mnfst%2Fmanifest | Trendshift

Manifest is becoming the self-healing layer for APIs. We're building a new product that fixes failed API requests on the fly, independently of the gateway. The open-source gateway stays available and maintained.

What is Manifest?

Manifest is an open-source LLM gateway 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.

  • ๐Ÿ”€ Custom Routing: API keys, Subscriptions, Local models, Custom providers
  • ๐Ÿ’พ Full Body Logs for Success and Error Messages
  • ๐Ÿ“Š Track every single dollar, setup notifications and limits
  • ๐Ÿš‘ Fallback on different models when queries fail, Self-heals your bad requests

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 โ€” the first account you create becomes the admin. Full self-hosting guide: docker/DOCKER_README.md.

Deploy with one click

PlatformNotes
RailwayBest path. Template includes Manifest, PostgreSQL, and S3-compatible storage for request recordings.
RenderBlueprint includes Manifest, PostgreSQL, and a persistent recording disk.
DigitalOceanApp Platform and PostgreSQL; provide a private Space for recordings.
AWSCloudFormation provisions ECS, RDS, and a private recording bucket.
GCPDeployStack provisions Cloud Run, Cloud SQL, and Cloud Storage.

Every deployment path now uses durable request-recording storage. Railway, AWS, GCP, and Fly.io provision it natively; Render, Coolify, Easypanel, Docker, and Apple Containers mount persistent storage. DigitalOcean, Heroku, and Koyeb collect external S3-compatible settings during setup. Volume-backed templates are single-instance; use S3-compatible storage before scaling horizontally.

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

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 35 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 OpenAI-compatible endpoint โ€” send "model": "auto" and Manifest picks the model.

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

ProviderAPI key / localSubscriptionModel catalog
OpenAIโœ…โœ… ChatGPT Plus / Pro / TeamGPT-5.6 (Sol / Terra / Luna), GPT-5.5, GPT-5.4, Codex, o-series
Anthropicโœ…โœ… Claude Max / ProClaude Opus 5, Sonnet 5, Fable 5, Haiku 4.5
Googleโœ…โœ… Sign in with GoogleGemini 3.6 Flash, 3.5 Flash, 3.1 Pro, Gemini 2.5
Google Vertex AIโœ…โ€”Gemini models via Vertex AI
Gemini Freeโœ… Managed keyโ€”Free Gemini models through Manifest's managed gateway
Metaโœ…โ€”Muse Spark 1.2 / 1.1 + Contributor route (Meta Model API)
xAIโœ…โœ… Grok subscriptionGrok 4.5, Grok 4.3, Grok Build, Grok 4.20
AWS Bedrockโœ…โ€”Claude, GPT, Kimi, MiniMax, Nemotron, Nova via Bedrock
Alibaba Cloud / Qwenโœ…โœ… Qwen Token PlanQwen 3.7 Max / Plus / Flash, DeepSeek, Kimi, GLM
DeepSeekโœ…โ€”DeepSeek V4 Pro, V4 Flash, V3.2, R1
Mistralโœ…โœ… Mistral VibeMistral Large, Medium 3.5, Devstral, Codestral
Moonshot (Kimi)โœ…โœ… Kimi Coding PlanKimi K3, K2.7 Code, Kimi for Coding
MiniMaxโœ…โœ… MiniMax Coding PlanMiniMax M3, M2.7, M2.5
Xiaomi MiMoโœ…โœ… MiMo Token PlanMiMo V2.5 Pro, V2.5, Flash
Z.aiโœ…โœ… GLM Coding PlanGLM 5.2, GLM 5.1, GLM 5 Turbo
BytePlusโ€”โœ… ModelArk Coding PlanArk Code, Seed Code, GLM, Kimi, DeepSeek, GPT-OSS
GitHub Copilotโ€”โœ… Copilot subscriptionClaude, GPT, Gemini, Grok via Copilot
Kiroโ€”โœ… Kiro subscriptionkiro/auto, Claude, DeepSeek, MiniMax, GLM, Qwen
Command Codeโ€”โœ… Command Code subscriptionClaude, DeepSeek V4, Qwen 3.7, Gemini, Kimi
ClinePassโ€”โœ… ClinePass subscriptioncline-pass/glm-5.2, Kimi, DeepSeek, MiMo, MiniMax, Qwen
NousResearchโ€”โœ… NousResearch subscriptionNousResearch Portal model catalog
OpenCode Goโ€”โœ… OpenCode GoDeepSeek V4, Qwen 3.7, GLM, Kimi, MiMo
Ollama / Ollama Cloud๐Ÿ–ฅ๏ธ Localโœ… Ollama CloudLocal tags: Llama, Qwen, Gemma. Cloud: DeepSeek V4, GLM, Kimi
LM Studio๐Ÿ–ฅ๏ธ Localโ€”Local GGUF models, port 1234
llama.cpp๐Ÿ–ฅ๏ธ Localโ€”Local GGUF models, port 8080
OpenRouterโœ…โ€”300+ models across labs
OpenCode Zenโœ…โ€”Curated Claude, GPT, DeepSeek, MiMo, Nemotron
Kiloโœ…โ€”Kilo Gateway catalog
Cerebrasโœ…โ€”GPT-OSS, GLM, Gemma on Cerebras inference
Fireworks AIโœ…โ€”DeepSeek V4, Kimi K2.7, Qwen 3.7, Nemotron
Groqโœ…โ€”Llama 4, Qwen 3.6, GPT-OSS, Gemma
Hugging Faceโœ…โ€”Open models through Hugging Face Inference Providers
NVIDIA NIMโœ…โ€”Nemotron 3, GLM, Kimi, MiniMax, Qwen
Pioneerโœ…โ€”OpenAI-compatible and fine-tuned Pioneer models
Customโœ…โ€”Any /v1/chat/completions or /v1/messages endpoint

Quick links

License

MIT

ๅ…ณไบŽ About

Connect Your Agents And Harnesses With Any Provider ๐Ÿฆš
aiai-ai-sdkanthropicbyokcheapcost-optimizationcost-trackinggatewayhermes-agentllm-observabilityllm-routeropen-sourceopenai-apiopenclawpersonal-aitoken-tracking

่ฏญ่จ€ Languages

TypeScript96.5%
CSS3.3%
Shell0.1%
Dockerfile0.1%
JavaScript0.0%
HTML0.0%

ๆไบคๆดป่ทƒๅบฆ Commit Activity

ไปฃ็ ๆไบค็ƒญๅŠ›ๅ›พ
่ฟ‡ๅŽป 52 ๅ‘จ็š„ๅผ€ๅ‘ๆดป่ทƒๅบฆ
3485
Total Commits
ๅณฐๅ€ผ: 340ๆฌก/ๅ‘จ
Less
More

ๆ ธๅฟƒ่ดก็Œฎ่€… Contributors