vLLora

A lightweight, real-time debugging tool for AI agents that traces every model and tool call through an OpenAI-compatible proxy, with a local UI for inspecting and analyzing interactions.

Visit website vllora.dev

vLLora is a local debugging tool for AI agents that collects traces of every model call and tool interaction as an agent's requests pass through it, working with LangChain, Google ADK, OpenAI and other major frameworks. Because it exposes an OpenAI-compatible chat completions API, an agent only needs to point its requests at vLLora, with API keys configured through vLLora's own web UI, to get debugging information for every interaction.

It installs through Homebrew, starts a server on port 9090 and a UI on port 9091, and includes a Rust client and streaming example for building against its OpenAI-compatible interface directly. Its stated feature set includes real-time tracing with live observability of calls, tool interactions and agent workflow.

More in AI evals

See all 269

Provenance gate
github.com
A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.
- Agent skills
- AI evals
JevBench
benchmarkheaven.com
A reproducible benchmark from Benchmark Heaven that ranks Jev-class typed decision models on intelligence, calibration, speed, and cost, with a published harness, scoring rules, and results.
- AI evals
LIFE FORGE - The Autonomous Flight Simulator for AI Agents
github.com
A co-evolutionary adversarial red-teaming tool for AI agents that uses quality-diversity evolutionary search to autonomously breed edge-case scenarios, testing whether an agent with tool access can be made to hallucinate, deadlock or leak funds.
- AI evals
- Security

More in AI evals

Provenance gate

JevBench

LIFE FORGE - The Autonomous Flight Simulator for AI Agents

Cookies