WilmerAI
WilmerAI is one of the oldest LLM semantic routers. It uses multi-layer prompt routing and complex workflows to allow you to not only create practical chatbots,
What is WilmerAI?
WilmerAI is one of the oldest LLM semantic routers. It uses multi-layer prompt routing and complex workflows to allow you to not only create practical chatbots, but to extend any kind of application that connects to an LLM via REST API. Wilmer sits between your app and your many LLM APIs, so that you can manipulate prompts as needed.
Overview of WilmerAI
What it is
WilmerAI is an application designed for advanced semantic prompt routing and complex task orchestration. It originated from the need for a router that could understand the full context of a conversation, rather than just the most recent message. Unlike simple routers that categorize a prompt based on a single keyword, WilmerAI's routing system analyzes the entire conversation history. This contextual understanding is made possible by its core: a node-based workflow engine. The routing itself is a workflow, categorizing through a sequence of steps defined in a JSON file. The route chosen kicks off another specialized workflow, which can call more workflows. Each node can orchestrate different LLMs, call external tools, run custom scripts, and call other workflows. To the client application, this entire multi-step process appears as a standard API call.
Key features
- Advanced Contextual Routing: Directs user requests using context-aware logic, including prompt routing at conversation start and in-workflow conditional routing based on entire conversation history.
- Core: Node-Based Workflow Engine: Processes requests using workflows defined as JSON files with sequences of nodes, enabling complex chained-thought processes.
- Multi-LLM & Multi-Tool Orchestration: Each node can connect to a different LLM endpoint or execute a tool, allowing orchestration of the best model for each part of a task.
- Modular & Reusable Workflows: Self-contained workflows for common tasks can be executed as a single node inside larger workflows.
- Stateful Conversation Memory: Uses a four-part memory system: chronological summary, rolling summary, searchable vector database, and state document.
- Adaptable API Gateway: Exposes OpenAI- and Ollama-compatible API endpoints for connecting existing front-end applications without modification.
- Privacy First Development: Designed with the principle of being completely private; only expected and actively configured calls are made.
Use cases
WilmerAI can be used to create practical chatbots and extend any application that connects to an LLM via REST API. It supports distributed LLMs, allowing multiple computers to work together in a single call. It enables iterative LLM calls to improve performance, such as automating follow-up questions in software development. It can also facilitate group chat to different LLMs and build complex workflows like a UX workflow where a user asks for a website.
Getting started
See the repository README for installation and quick-start instructions.
License and pricing
WilmerAI is open source under the GPL-3.0 license.
Based on the project's public README and repository metadata.
