agent-xray is an open-source CLI tool that enables AI developers to debug, grade, and replay traces from AI agents locally. Below are 17 llm eval & observability apps with similar functionality to agent-xray, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
agentlens-xray is an open-source tool for debugging AI agents locally. It provides fork and replay capabilities, observability, and tracing for LLM-based agents, helping developers understand and improve agent behavior.
agent-probe-ai is an open-source CLI tool for adversarial resilience testing of AI agents. It evaluates agent robustness against attacks like memory poisoning and tool misuse, helping AI researchers and security engineers identify vulnerabilities.
agent-debug is an open-source CLI tool for diagnosing failures in AI agent workflows. It provides root cause analysis and actionable fix suggestions, helping AI developers and researchers debug and improve their agent systems.
AgentX - Native compiled Python agent framework
trajex is an open-source toolkit and format for recording, analyzing, and asserting AI agent execution traces. It enables developers and researchers to observe, test, and evaluate LLM-based agent behaviors, supporting integration with frameworks like LangChain and OpenAI.
agent-dump is an open-source CLI tool that enables developers to export and manage session data from AI coding assistants. It is designed for developers who need to analyze or back up their coding assistant interactions.
agent-triage is an open source tool for ranking and diagnosing failures in multi-agent systems. It provides a CLI, web dashboard, OTLP receiver, and optional LLM-based root-cause analysis, helping AI engineers quickly identify and prioritize issues.
axm-ast is a command-line tool that provides AST introspection capabilities for AI agents, leveraging tree-sitter. It helps developers and researchers analyze code structure programmatically.
agentrepocoach is an open-source CLI tool that analyzes codebases to determine their readiness for AI agent integration. It provides a readiness score and actionable coaching to help developers improve code quality for agent compatibility.
agent-diagnostics is an open-source framework for analyzing and annotating the behavior and reliability of coding agents. It provides tools for benchmarking, taxonomy creation, and structured evaluation, helping researchers and developers understand agent performance.
replay-agent is an open-source CLI tool that allows developers to record and replay traces of LLM agent executions, enabling deterministic regression testing. It is framework-agnostic and integrates natively with pytest, making it ideal for AI developers and QA engineers.
Local web viewer for AI agent sessions
Thin CLI + MCP client for Agent-CoreX — execute any task with a single query
agentsec-eval is an open-source CLI framework for evaluating the security of AI agents. It provides adversarial test runners, server-side audits, and scoring mechanisms to help researchers and developers identify vulnerabilities such as prompt injection and improve agent robustness.
AgentX is a web-based social network designed for autonomous AI agents to interact, post updates, and collaborate in real time. It features public posts, trust scores, federated feeds, and developer tools, making it a hub for developers and organizations working with AI agents.
exara-agent is a local-first autonomous AI agent designed for programming and system automation. It supports running against local models like Ollama or vLLM, as well as OpenAI-compatible APIs, and features native tool calling, MCP protocol support, and extensible skills. Ideal for developers seeking programmable AI automation with privacy and flexibility.
agentassay is an open-source Python package designed for formal regression testing of non-deterministic AI agent workflows. It provides tools for verifying the reliability and correctness of agent-based systems, supporting stochastic and CI/CD testing scenarios. Ideal for AI developers and QA engineers working with complex agent architectures.
