Terminal Bench Python Packages

harbor-rewardkit

Framework for evaluating and improving agents

harbor-langsmith

Framework for evaluating and improving agents

coder-eval

Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.

harbor-atif2otel

Framework for evaluating and improving agents

agent-sandbox-e2b

Fast, Multi-Cloud Sandbox Engine for AI Agents

agent-sandbox-harbor

Fast, Multi-Cloud Sandbox Engine for AI Agents

spoox

Spoox CLI - Terminal Agent - SPlit lOOp eXand agent

harness-arena

Your model, many harnesses, many benchmarks.

todoforai-edge-cli

Open-source AI agent that runs on your own computer and does your tasks. Any model (Claude, GPT, Gemini, Grok, Ollama), drives your real browser, shell, files, DOCX/XLSX.