ToolsCompaniesAbout

Results for “agent evaluation”

34 tools in this category · Updated

“agent evaluation”CodingOpen sourceShowing 34 tools
  • Unity ML-Agentsby UnityTrain intelligent agents inside Unity games and simulationsFree
  • Kitaruby ZenmlFind gaps in agent evaluations and replay proposed fixesFreemium
  • Flower Agentby FlowerYC W23Build and run agent applications with managed context and toolsUnknown
  • PayPal Agent Toolkitby PayPalGive AI agents controlled access to PayPal payment operationsUnknown
  • Deep Agentsby LangChainOpen-source agent harness for long-running, multi-step tasksFree
  • Cognizant Neuro Sanby CognizantBuild and coordinate networks of specialized AI agentsFree
  • CAMEL-AIby CAMEL-AIBuild and study multi-agent systems in PythonFree
  • ZenMLby ZenmlRun reproducible AI pipelines and agents on your chosen infrastructureFreemium
  • NVIDIA NeMoby NVIDIAOpen libraries for specializing, evaluating, governing, and deploying AI agentsUnknown
  • LangGraphby LangChainOpen-source Python library for orchestrating stateful, long-running AI agentsFree
  • LangChainby LangChainOpen source framework for building agents that work with many models and toolsFree
  • Evidently AIby Evidently AIYC S21Open-source AI evaluation and observability for LLMs and ML modelsUnknown
  • cqby Mozilla.aiShare reviewed operational knowledge across AI agentsFree
  • Klavis MCPby Klavis AIYC X25Connect agents to application tools through open-source MCP integrationsFree
  • Aviaryby FutureHouseOpen-source Python gymnasium for building custom language agent environments.Free
  • AG2by AG2Build cooperating AI agents with a Python frameworkFree
  • RubyLLMby RubyLLMBuild model-powered applications and agents in RubyFree
  • Bloomby AnthropicGenerate behavioral evaluation suites to test how AI models act across varied scenarios.Free
  • AutoGenby MicrosoftArchived open-source Python and .NET framework for multi-agent AI applicationsFree
  • Inkeepby InkeepYC W23Build customer-experience agents in a visual editor or TypeScriptContact sales
  • Tabstack Piloby MozillaRun browser tasks from natural-language instructionsFree
  • mcp-useby ManufactYC S25Build MCP servers and interactive apps for AI clientsFree
  • mcpdby Mozilla.aiManage MCP tool servers through a reproducible runtimeFree
  • NVIDIA Cosmosby NVIDIAOpen world foundation models, datasets and tools for building physical AI.Free