Harbor
Harbor Can Now Run Every Agent Eval Task in Docker Sandboxes
Harbor, an open-source framework for evaluating AI agents, can now run every eval task inside Docker Sandboxes, according to Docker. The company says the microVM-based…
LangChain lifts coding agent from Top 30 to Top 5 by changing only the harness
LangChain says its coding agent, deepagents-cli, climbed from outside the Top 30 to the Top 5 on Terminal Bench 2.0 by changing only the harness around the model. The…
Arize Benchmarks AI Agents With Harbor and Phoenix Plugin
Arize AI has described how it benchmarks its PXI coding agent, along with MCP servers, skills and CLIs, using the open-source Harbor framework and a plugin that records…