Manifest
Manifest is an open-source LLM (Large Language Model) router specifically built for OpenClaw. It optimizes AI expenditures by intercepting queries and routing them to the most cost-effective model based on the complexity of the task, potentially saving users up to 70% on token costs. The system analyzes queries locally in less than 2ms to ensure minimal latency. It prioritizes privacy by performing query scoring on the user's machine and using a blind proxy architecture for its cloud version. Additionally, it allows users to track costs, set usage limits, and export data using the OpenTelemetry standard.
Open-source LLM router for OpenClaw that optimizes model routing to save up to 70% costs.
- Reducing API token costs for OpenClaw users
- Ensuring data privacy by scoring queries locally
- Preventing high-cost models from being used for simple search or text tasks
- Monitoring AI budgets across development teams
- Users can get started by installing the native OpenClaw plugin via a single command. Once installed
- Manifest automatically intercepts queries
- analyzes them locally
- and directs them to the most appropriate model. Users can then use the dashboard to monitor costs and set budget alerts.
Resources and tools for building with Google's AI models.
Open-source, offline ChatGPT alternative prioritizing privacy and customization.
Access to DeepSeek R1, an open-source AI model for advanced reasoning.
Private, uncensored AI for generating text, images, code, and characters.
DeepSeek is an AI company providing foundation models and APIs for AI applications.
Open-source 15B parameter AI model for joint video and synchronized audio generation.
Huawei's open-source AI framework for full-scenario deep learning.
Open-source fine-tuning & reinforcement learning for LLMs. 🦥
Private AI chat with 20+ open-source models, focused on data privacy.
