LLM evaluation and quality assurance framework for GitHub Copilot SDK — judge-based scoring, prompt injection detection, benchmark suites, and CI/CD eval pipelines, all routed through copilot-guard.
GitHub Action for evaluating MCP server tool calls using LLM-based scoring
LLM eval & testing toolkit
GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.
GitHub Copilot CLI executable for linux-x64
No description provided.
Test your LLM-powered apps with a TypeScript-native, Vitest-based eval runner. No API key required.
Harness-backed AI testing on top of Vitest.
Lightweight runtime quota and usage guard for GitHub Copilot SDK integration.
CLI entry point for AgentV
Your AI pair programmer
Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c
GitHub Copilot CLI executable for win32-x64
A module used for interacting with the GitHub Copilot API.
Offline evaluation framework for Output.ai workflows
Stage-gated AI pipeline orchestration with multi-agent coordination, prompt contracts, cost-aware routing, and observability — all calls guarded by @stackforgeai/copilot-guard.
Composable skill engineering framework for GitHub Copilot SDK — define, register, compose, and execute reusable AI skills with typed I/O, context awareness, caching, and full observability, all routed through copilot-guard.
A library for running evaluations for AI use cases
GitHub Copilot CLI executable for linuxmusl-x64
GitHub Copilot CLI executable for darwin-arm64
Production-grade AI orchestration framework for GitHub Copilot SDK — flows, prompts, tools, structured output, middleware, and observability, all routed through copilot-guard.
Copilot Language Server binary for darwin-arm64
Universal library for evaluating AI models
Copilot Language Server binary for linux-x64