200 free apps like Composo, closest match first.
Mnemosyne
Evidence-backed memory for AI agents: local-first recall, temporal history
Blave Agent
Quant infrastructure for AI agents — a free, open-source desktop workspace…
IsReady.AI
Tailored solutions combining radical usability
Promptulate
Lightweight Large language model automation
prompt-engineering
Expert guide on prompt engineering patterns, best practices
mle-workflow
Production machine-learning engineering workflow for data contracts
LLM Wiki
Knowledge Bases for AI Agents
Adrian
Open-source runtime AI agent security tool
AI Collab Playbook
Practical AI collaboration playbook for research, writing, reading
Agent Systems Handbook
A practical AI agents handbook covering agent systems, agentic workflows
agent-architecture-audit
Full-stack diagnostic for agent and LLM applications
course-guide
Topic router for the AI Engineering from Scratch curriculum
Gem Team
Turn AI coding into an engineering process
teach
Explain a body of work plainly so a person actually understands it
Happy Operators
We teach AI and Automation to businesses and users
AI Infra Junior Engineer Learning
AI Infrastructure Junior Engineer Learning Track
plan-design-review
Senior Designer review: rates each design dimension 0-10
check-understanding
Phase quiz for AI Engineering from Scratch
agent-inspect
Local evidence debugger and trajectory-test toolkit
eval-harness
Eval-driven development (EDD) framework for AI coding sessions
Primitive Bench
The marketplace for verifiable AI outcomes: state a task
LLM Dojo
Learn AI engineering by experimenting with the systems you build
Lnwjud
Local AI-agent runtime & MCP gateway
huggingface-community-evals
Run evaluations for Hugging Face Hub models
skill-doctor
Grades agent skills by scoring agent conversations for efficiency, code quality
prompt-engineer
Expert in designing effective prompts for LLM-powered applications
continual-learning
Orchestrate continual learning
aiconfig-online-evals
DEPRECATED redirect — this skill was renamed to online-evals
MartinLoop
Open-source control plane for AI coding agents
arize-prompt-optimization
Optimizes, improves, and debugs LLM prompts
Stoneforge
Open-source orchestration for AI coding agents
fine-tuning-expert
Fine-tuning LLMs, training custom models
langsmith-dataset
INVOKE THIS SKILL when creating evaluation datasets
huggingface/hugging-face-evaluation
Model evaluation with vLLM/lighteval and eval tables
learn
Interactive lesson tutor for the AI Engineering from Scratch curriculum
evaluation-methodology
PluginEval quality methodology, covering dimensions, rubrics
managed-deep-agents
INVOKE THIS SKILL when building, testing
start-learning
One-time onboarding for the AI Engineering from Scratch curriculum
Opentraces
A local-first evidence layer for agent work, capturing what the agent sees
ai-engineer
Build production-ready LLM applications, advanced RAG systems
gan-style-harness
GAN-inspired Generator-Evaluator agent harness
Prefactor
Evaluate your AI Agents in
agentic-engineering
Operate as an agentic engineer
AI-RnD
Find AI research papers, list your own, and engage in AI discussions
model-recommendation
Analyze chatmode or prompt files
health
Audits agent config, instruction drift, hooks or MCP, and AI maintainability
agent-governance
Declarative policies, intent classification
egregore
Autonomous agent orchestrator: parallel worktree execution
huggingface-llm-trainer
Train or fine-tune language and vision models using TRL
investorskills
Investing judgment skills: filtering opportunities, sizing risk