200 free apps like Hyperparam, closest match first.
Agenttrace
Local-first TUI for inspecting AI coding agent sessions, costs, tokens, latency
Best AI Agents Directory
Curated Collection of the Best AI Agents to Boost Your Workflow
Abyss
Transform your Python scripts into user-friendly AI Solutions!
langsmith-dataset
INVOKE THIS SKILL when creating evaluation datasets
TestMyPrompt
The Best AI Prompt Management Tool For Prompt Designers
agent-pulse
Use Agent Pulse to inspect local AI-agent activity across Hermes, Claude Code
Dremio
Create custom reports, build interactive dashboards
managed-deep-agents
INVOKE THIS SKILL when building, testing
huggingface-trackio
Track and visualize ML training experiments with Trackio
health
Audits agent config, instruction drift, hooks or MCP, and AI maintainability
tigris-agent-kit
Building AI agent storage workflows on Tigris
Agent Mastery
Master the Best AI Tools. Learn, Compare, and Stay Ahead
data-designer
Create a dataset, generate synthetic data, or build a data generation pipeline
langfuse
Interact with Langfuse and access its documentation: tracing, monitoring
Optuna Dashboard
Real-time Web Dashboard for Optuna
building-pydantic-ai-agents
Build AI agents with Pydantic AI
RAGAS
Evaluation framework for your AI Application
kibana-anomaly-detection
Elastic ML anomaly detection
agent-architecture-audit
Full-stack diagnostic for agent and LLM applications
llm-evaluation
Implement comprehensive evaluation strategies for LLM applications
ai-ethics-governance-specialist
Implement AI ethics frameworks, governance policies
langsmith-fetch
Debug LangChain and LangGraph agents by fetching execution traces
memory-management
AgentDB memory system with HNSW vector search
mle-workflow
Production machine-learning engineering workflow for data contracts
data-context-extractor
Generate or improve a company-specific data analysis skill
huggingface/hugging-face-dataset-viewer
Browse and query HF datasets with the Dataset Viewer API
phoenix-cli
Debug LLM applications using the Phoenix CLI
querying-aws-sagemaker-catalog
Runs SQL analytics on SageMaker Catalog asset metadata tables exported as Apache
Mass.new
AI First GHL alternative that builds, tracks, learns
mantis-reflect
Extracts learnings from execution trajectories at the end of a Mantis loop
analyze
Answer data questions -- from quick lookups to full analyses
eval-driven-dev
Improve AI application with evaluation-driven development
eval-audit
Audit an LLM eval pipeline and surface problems: missing error analysis
Honeycomb
Identify performance issues, visualize and troubleshoot in real-time
explore-data
Profile and explore a dataset to understand its shape, quality, and patterns
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements
harness-creator
Build, audit, and improve harnesses
AI Supermarket
Compare 107+ AI tools side-by-side with pricing and reviews
phoenix-evals
Build and run evaluators for AI/LLM applications using Phoenix
Labml
Monitor deep learning model training and hardware usage from your mobile phone
aiconfig-ai-metrics
DEPRECATED redirect — this skill was renamed to built-in-metrics
dt-obs-genai
Analyze & debug GenAI/LLM apps: token cost & caching by prompt
observability
Instruments assistant-ui AI SDK backend routes
turbo-builder
Build and deploy new Goldsky Turbo pipelines: requirements, dataset selection
ai-agent-workspace
Give every AI agent its own computer: a persistent workspace
debug-my-harness
Diagnose why an agent harness misbehaved
Rakam
Custom analytics platform
Vibe Code Pipeline
Learn how AI agents work by watching them work
HQ Data Profiler
Analyze data with 20+ metrics and ML-powered anomaly detection
Cloudoora GenAI Platform
Enterprise AI Deployment & Infrastructure Platform