by indemn-ai
CLI, MCP server, and plugin for managing Indemn AI agents
npm:@indemn/cli · local package629/wkpublished 26 h ago
Evaluate model or agent outputs.
CLI, MCP server, and plugin for managing Indemn AI agents
MCP server that exposes MCPLab evaluation tools — query runs, results, and traces via the Model Context Protocol
MCP server that exposes the Langfuse REST API as tools — query traces, observations, sessions, scores, prompts, datasets, and metrics from any MCP client.
Run LLM tool-use evaluations against MCP servers with the Vercel AI SDK
Pocket Model from your terminal and your agent: find the smallest model that does your task, train it on your data, and serve it. CLI and MCP server.
TypeScript MCP server for Canvas LMS — 187 tools across 42 domains.
Model Context Protocol server for ZeroBounce email validation, verification, and intelligence. Provides comprehensive email validation, AI scoring, email finder, domain search, and bulk processing capabilities for AI coding assistants.
Author verifiable eval records through a draft→review→revise→submit loop with enforced graders.
Hire human data labelers, RLHF annotators, and evaluators from your coding agent.
Persistent project context for Claude. IANA-registered .faf format.
Run, watch, and meter coding agents — Claude Code, OpenCode, Kiro, Codex CLI, Gemini CLI, Prime Agent — with normalized events, cost accounting, A/B experiment/variant comparison, external run sources, and replayable run artifacts.
Scores a company against your ICP with weighted signals. Returns score, tier, and breakdown.
Combines hiring and tech-stack signals into one composite GTM score. Clay-ready output.
TypeScript SDK and MCP server for CourtListener API
TokRepo MCP: tokrepo_discover, tokrepo_verify, tokrepo_install_plan for reusable AI assets.
A deterministic benchmark MCP server for agent evaluation workflows.
The governed agent operating system that turns rough product ideas into approved requirements, specifications, delivery, and evidence-backed software.
CLI + MCP server for OpenRouter models: prices, benchmarks, context and comparisons
Harness de evals para servidores MCP: seleção de tool em turno único (catálogo, fixtures, scorer, gate, runner via Messages API) e SESSÃO LONGA (loop client-side por stdio, A/B do bloco `retrieval`, métrica de chamadas ruins por tarefa, teto de gasto, NDJ
The adaptive AI harness for React Native — project-aware SDLC intelligence for any agent