Manifest
A smart model router for AI apps that cuts costs up to 70% by routing queries to the best model.
Smart Download
Visit Project Homepage
No installer available yet — head to the source repository
Smart model router cuts AI costs by 70%, mixes providers and local models.
Core Features
- Intelligent routing based on complexity, specificity, and custom headers
- Mix providers: API keys, subscriptions, local models
- Track spending with notifications and limits
- Automatic fallback on model failure
- Supports 300+ models across 16 providers
What It Can't Do
- •Beta software, some features may be unstable. 2. Routing rules need tuning for optimal savings. 3. Self-hosted requires server maintenance.
Use Cases
- Startups reducing AI costs by blending subscriptions and pay-per-use
- Developers using local models for simple tasks to save money
- Enterprises centralizing model access and budget control
Manifest is an intelligent model routing layer for AI applications and agents. It automatically selects the most cost-effective model for each query based on complexity, specificity, and custom rules, reducing AI API costs by up to 70%. Supports 300+ models across 16 providers including OpenAI, Anthropic, Google, local models (Ollama, LM Studio), and subscriptions (ChatGPT Plus, Claude Pro). Offers both cloud and self-hosted options with Docker. Features include provider mixing, fallback handling, spending tracking, and custom routing headers.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Double-click the downloaded installer and follow the prompts
Step 1: Sign up at app.manifest.build for cloud, or run the Docker install script for self-hosted
Step 2: Add your API keys, subscriptions, or local model endpoints in the dashboard
Step 3: Replace your API endpoint with /auto — Manifest routes each request to the best model
- Step 1: Sign up at app.manifest.build for cloud, or run the Docker install script for self-hosted
- Step 2: Add your API keys, subscriptions, or local model endpoints in the dashboard
- Step 3: Replace your API endpoint with /auto — Manifest routes each request to the best model
Checksum not available
This project has not published a SHA-256 checksum on its GitHub Release page
SHA256 Checksum
No checksum available
Download directly from GitHub Releases and verify file integrity yourself
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
For Docker: docker rm -f manifest and remove volumes; for cloud: just delete your account.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Having issues? Check the FAQ below
4 FAQs
Similar Projects
AnythingLLM
Chat with your docs, use AI agents, multi-user support, runs locally with zero setup.
LocalAI
LocalAI is the open-source AI engine to run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. Drop-in API compatibility with OpenAI, Anthropic, and ElevenLabs.
daily_stock_analysis
An open-source AI stock analysis system for A/H/US markets that generates daily decision dashboards and pushes them to WeChat Work, Feishu, Telegram, Discord, Slack, or email. Deploy via GitHub Actions for free.