PrimeIntellect-ai/verifiers

Health v2 · maintenance only

Adoption not part of the score

4559 stars · 654 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

verifiers is a Python library for creating environments to train and evaluate large language models with reinforcement learning. It integrates with Prime Intellect's Environments Hub, prime-rl training framework, and hosted training platform.

Use cases

• create RL environments for training LLMs
• evaluate LLMs on custom tasks
• train language models with reinforcement learning
• benchmark LLM reasoning and agent behavior
• build verifiable reward environments for RLHF-style training

When to choose

• you need to train LLMs with RL using custom environments
• you want a standard library for LLM evals and verifiers
• you use Prime Intellect's prime-rl or Environments Hub ecosystem

When to avoid

• you only need simple supervised fine-tuning without RL
• you need a general-purpose ML training framework unrelated to LLMs
• you want a turnkey hosted product rather than a Python library

Facets

library · maturity active

llm-training machine-learning testing benchmarking agent-framework large-language-models reinforcement-learning artificial-intelligence machine-learning python rl-environments llm-evals reinforcement-learning-environments prime-rl environments-hub

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PrimeIntellect-ai/verifiers")