vllora
Debug your AI agents
vLLora is a lightweight, real-time debugging and observability platform for AI agents that provides tracing, analysis, and monitoring capabilities. It acts as an OpenAI-compatible proxy server that captures and visualizes every interaction your AI agents make, supporting LangChain, Google ADK, OpenAI, and other major frameworks. The platform includes full Model Context Protocol (MCP) support, enabling developers to connect external tools and debug agent workflows through HTTP and SSE. vLLora runs locally on your machine, offering a web UI for configuring API keys and viewing live traces of agent behavior.
Key Features
Use Cases
- 01Debugging multi-step AI agent workflows to identify where failures or unexpected behavior occurs
- 02Monitoring LangChain agent tool calls and decision-making in real-time
- 03Tracing OpenAI API requests from custom AI applications during development
- 04Analyzing token usage and response patterns across multiple agent interactions
- 05Integrating external tools through MCP servers and observing their usage by agents
- 06Testing and optimizing agent prompts by reviewing complete conversation traces
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
vllora — FAQ
What is vLLora MCP server?+
vLLora is a debugging and observability platform for AI agents that supports the Model Context Protocol. It acts as a proxy server that captures and visualizes agent interactions, tool calls, and workflow traces in real-time while maintaining compatibility with OpenAI-style APIs.
How do I install vLLora?+
Install vLLora using Homebrew by running 'brew tap vllora/vllora' followed by 'brew install vllora'. After installation, start the server with the 'vllora' command, which launches the API on port 9090 and the UI on port 9091.
Which AI clients and frameworks work with vLLora?+
vLLora works with any framework or client that supports OpenAI-compatible APIs, including LangChain, Google ADK, OpenAI SDK, and custom Rust applications. It also supports Model Context Protocol (MCP) servers for external tool integration.
Do I need API keys to use vLLora?+
Yes, you need API keys from your chosen AI provider (such as OpenAI). Configure these keys through the vLLora web UI at localhost:9091 or set them as environment variables like VLLORA_OPENAI_API_KEY.
Is vLLora free to use?+
vLLora is source-available and self-hostable under the Elastic License 2.0 (ELv2), which allows free use for most purposes. For enterprise licensing or commercial redistribution, contact the team at hello@vllora.dev.
How does vLLora capture agent traces?+
Point your AI agent's API calls to vLLora's proxy endpoint (http://localhost:9090/v1/chat/completions instead of the direct provider endpoint). vLLora forwards requests to the actual provider while capturing all interaction data for the debugging UI.
How do I install vllora?+
Open the source repository on GitHub and follow its README. vllora is a mcp server — MCP Agents Market links you directly to the official repo.
Is vllora free?+
vllora is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.