Connect Your Agents And Harnesses With Any Provider 🦚
Manifest is an open-source LLM routing gateway, available as a self-hosted Docker container or cloud service, that sits between AI applications and model providers to reduce inference costs by up to 70%. It routes each request to the most appropriate model based on query complexity, specificity, and custom HTTP headers, supporting over 300 models across 18 providers including Anthropic (Claude Opus, Sonnet, and Haiku), OpenAI, Google Gemini, DeepSeek, and local models, all exposed through a single `/auto` endpoint. Users can supply their own API keys, reuse existing paid subscriptions like Claude Max or Pro, or run models locally, mixing credential types freely. The platform includes per-request cost tracking, spending notifications, budget limits, and automatic fallback when a model call fails. Developers building agents or AI applications who want provider flexibility and detailed cost observability without rewriting client code are the primary audience, since Manifest accepts standard OpenAI and Anthropic-compatible requests.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/mnfst/manifestResumen de Tools
<p align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/mnfst/manifest/HEAD/.github/assets/logo-white.svg" />
<source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/mnfst/manifest/HEAD/.github/assets/logo-dark.svg" />
<img src="https://raw.githubusercontent.com/mnfst/manifest/HEAD/.github/assets/logo-dark.svg" alt="Manifest" height="53" title="Manifest"/>
</picture>
</p>
<p align="center">
Reduce your AI costs
</p>
<p align="center">
<span><img src="https://img.shields.io/badge/status-beta-yellow" alt="beta" /></span>
<a href="https://github.com/mnfst/manifest/stargazers"><img src="https://img.shields.io/github/stars/mnfst/manifest?style=flat" alt="GitHub stars" /></a>
<a href="https://hub.docker.com/r/manifestdotbuild/manifest"><img src="https://img.shields.io/docker/pulls/manifestdotbuild/manifest?color=2496ED&label=docker%20pulls" alt="Docker pulls" /></a>
<a href="https://hub.docker.com/r/manifestdotbuild/manifest/tags"><img src="https://img.shields.io/docker/image-size/manifestdotbuild/manifest/latest?color=2496ED&label=image%20size" alt="Docker image size" /></a>
<a href="https://github.com/mnfst/manifest/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/mnfst/manifest/ci.yml?branch=main&label=CI" alt="CI status" /></a>
<a href="https://app.codecov.io/gh/mnfst/manifest"><img src="https://img.shields.io/codecov/c/github/mnfst/manifest?label=coverage" alt="Codecov" /></a>
<a href="LICENSE"><img src="https://img.shields.io/github/license/mnfst/manifest?color=blue" alt="license" /></a>
<a href="https://discord.gg/FepAked3W7"><img src="https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&logoColor=white" alt="Discord" /></a>
</p>
<p align="center">
<a href="https://trendshift.io/repositories/12890" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12890" alt="mnfst%2Fmanifest | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
</p>
## What is Manifest?
Manifest is a smart model router for agents and AI applications that redirects each query to the right model, saving up to 70% in AI costs.
- 🔀 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](https://app.manifest.build) and follow the guide.
### Self-hosted
Manifest ships as a [Docker image](https://hub.docker.com/r/manifestdotbuild/manifest). One command:
```bash
bash <(curl -sSL https://raw.githubusercontent.com/mnfst/manifest/main/docker/install.sh)
```
Open [http://localhost:2099](http://localhost:2099) and sign up — the first account you create becomes the admin. Full self-hosting guide: [docker/DOCKER_README.md](docker/DOCKER_README.md).
> The legacy `manifest` npm package is deprecated and no longer published.
## Providers
Manifest connects to **300+ models across 18 providers** plus any custom provider (OpenAI/Anthropic compatible). Bring your own API key, reuse a paid subscription you already have, or run models locally — all routed through
the same `/auto` endpoint.
| Provider | API key | Subscription | Featured models |
| ---------------------------------------------------------------------------------------- | :------: | :--------------------------- | :------------------------------------------------------ |
| [**OpenAI**](https://platform.openai.com/) | ✅ | ✅ ChatGPT Plus / Pro / Team | gpt-5, gpt-5-mini, o4, o4-mini |
| [**Anthropic**](https://www.anthropic.com/) | ✅ | ✅ Claude Max / Pro | claude-opus-4-7, claude-sonnet-4-6, claude-haiku-4-5 |
| [**Google**](https://ai.google.dev/) | ✅ | — | gemini-2.5-pro, gemini-2.5-flash, gemini-2.0-flash |
| [**xAI**](https://x.ai/) | ✅ | — | grok-4, grok-3, grok-code-fast |
| [**DeepSeek**](https://www.deepseek.com/) | ✅ | — | deepseek-v3.2, deepseek-r1 |
| [**Mistral**](https://mistral.ai/) | ✅ | — | mistral-large, codestral, magistral |
| [**Qwen** (Alibaba Cloud)](https://www.alibabacloud.com/en/solutions/generative-ai/qwen) | ✅ | — | qwen3-max, qwen3-coder, qwq-32b |
| [**Moonshot** (Kimi)](https://kimi.ai/) | ✅ | ✅ Kimi Coding Plan | kimi-k2, kimi-for-coding, moonshot-v1-128k |
| [**MiniMax**](https://www.minimax.io/) | ✅ | ✅ MiniMax Coding Plan | minimax-m2, abab7-chat-preview |
| [**Xiaomi MiMo**](https://platform.xiaomimimo.com/) | ✅ | ✅ MiMo Token Plan | mimo-v2.5-pro, mimo-v2.5, mimo-v2-flash |
| [**Z.ai** (Zhipu)](https://z.ai/) | ✅ | ✅ GLM Coding Plan | glm-4.6, glm-4.5-air |
| [**BytePlus**](https://www.byteplus.com/en/activity/codingplan) | — | ✅ ModelArk Coding Plan | ark-code-latest, bytedance-seed-code, deepseek-v4-flash |
| [**OpenCode**](https://opencode.ai/) | — | ✅ Go subscription | Routes via OpenCode Go catalog |
| [**Ollama**](https://ollama.com/) | 🖥️ Local | ✅ Ollama Cloud | Any GGUF model, port `11434` |
| [**LM Studio**](https://lmstudio.ai/) | 🖥️ Local | — | Any GGUF model, port `1234` |
| [**llama.cpp**](https://github.com/ggml-org/llama.cpp) | 🖥️ Local | — | Any GGUF model, port `8080` |
| [**OpenRouter**](https://openrouter.ai/) | ✅ | — | Routes to 300+ models across labs |
| [**GitHub Copilot**](https://github.com/features/copilot) | — | ✅ Copilot subscription | OAuth, no API key needed |
| **Custom** (OpenAI/Anthropic-compatible) | ✅ | — | Any `/v1/chat/completions` or `/v1/messages` endpoint |
## Quick links
- [Docs](https://manifest.build/docs)
- [Discord](https://discord.com/invite/FepAked3W7)
- [Discussions](https://github.com/mnfst/manifest/discussions)
- [Contributing](CONTRIBUTING.md)
- [GitHub](https://github.com/mnfst/manifest)
## License
[MIT](LICENSE)
Lo que la gente pregunta sobre manifest
¿Qué es mnfst/manifest?
+
mnfst/manifest es tools para el ecosistema de Claude AI. Connect Your Agents And Harnesses With Any Provider 🦚 Tiene 6.9k estrellas en GitHub y se actualizó por última vez today.
¿Cómo se instala manifest?
+
Puedes instalar manifest clonando el repositorio (https://github.com/mnfst/manifest) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar mnfst/manifest?
+
Nuestro agente de seguridad ha analizado mnfst/manifest y le ha asignado un Trust Score de 100/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene mnfst/manifest?
+
mnfst/manifest es mantenido por mnfst. La última actividad registrada en GitHub es de today, con 99 issues abiertos.
¿Hay alternativas a manifest?
+
Sí. En ClaudeWave puedes explorar tools similares en /categories/tools, ordenados por popularidad o actividad reciente.
Despliega manifest en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/mnfst-manifest)<a href="https://claudewave.com/repo/mnfst-manifest"><img src="https://claudewave.com/api/badge/mnfst-manifest" alt="Featured on ClaudeWave: mnfst/manifest" width="320" height="64" /></a>Más Tools
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies