aiming-lab/Agent0

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1256 stars · 150 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Agent0 Series is a research framework for training self-evolving LLM agents from zero external data via tool-integrated reasoning and co-evolution between a curriculum agent and an executor agent. It includes Agent0 for text reasoning and Agent0-VL for multimodal vision-language reasoning with solver-verifier self-repair.

Use cases

• train an llm agent without human-curated training data
• self-improve a language agent on math reasoning benchmarks
• evolve agents via curriculum and executor co-evolution
• build tool-integrated reasoning agents
• train a vision-language agent that self-evaluates and self-repairs
• reproduce research on autonomous agent evolution

When to choose

• you want to train agents with zero external training data
• you need tool-integrated multi-turn reasoning agents
• you are doing research on self-improving or co-evolving agents
• you need multimodal (vision-language) agent self-evolution

When to avoid

• you need a production-ready agent framework with managed infrastructure
• you lack GPU resources for LLM training
• you want a no-code or plug-and-play agent builder
• you need small-model or CPU-only training

Facets

framework · maturity active

agent-framework llm-training machine-learning prompt-engineering artificial-intelligence large-language-models machine-learning python cross-platform self-evolving-agents zero-data tool-integrated-reasoning curriculum-learning vision-language research-code co-evolution ai-agents research linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="aiming-lab/Agent0")