--- title: "MetaClaw vs LLM-Agent-Paper-List" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/aiming-lab-metaclaw-vs-woooodyy-llm-agent-paper-list" tools: ["aiming-lab-metaclaw", "woooodyy-llm-agent-paper-list"] --- # MetaClaw vs LLM-Agent-Paper-List *GraphCanon updated Sep 20, 2026* ## Verdict Pick MetaClaw if metaClaw enables AI agents to evolve through continuous learning and interaction; pick LLM-Agent-Paper-List if lLM-Agent-Paper-List is a curated repository of essential papers on large language model-based agents, focusing on AgentGym, a framework for developing and training LLM agents through reinforcement learning. [MetaClaw](https://arxiv.org/abs/2603.17187) reports 3.5k GitHub stars, 454 forks, and 17 open issues, last pushed Jun 7, 2026. [LLM-Agent-Paper-List](https://arxiv.org/abs/2309.07864) has 8.2k stars, 499 forks, and 32 open issues, last pushed Sep 12, 2025. Figures are from public GitHub metadata via [MetaClaw's repository](https://github.com/aiming-lab/MetaClaw) and [LLM-Agent-Paper-List's repository](https://github.com/WooooDyy/LLM-Agent-Paper-List). | | [MetaClaw](/tools/aiming-lab-metaclaw.md) | [LLM-Agent-Paper-List](/tools/woooodyy-llm-agent-paper-list.md) | | --- | --- | --- | | Tagline | Simply converse with your agent, it learns and evolves | Must-read papers for LLM-based agents. | | Stars | 3,493 | 8,222 | | Forks | 454 | 499 | | Open issues | 17 | 32 | | Language | Python | - | | Adopt for | MetaClaw enables AI agents to evolve through continuous learning and interaction. | LLM-Agent-Paper-List is a curated repository of essential papers on large language model-based agents, focusing on AgentGym, a framework for developing and training LLM agents through reinforcement learning. | | Persona | - | - | | Runtime | - | - | | License | MIT | - | | Categories | AI Agents, Model Training | AI Agents, Evaluation & Observability, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [MetaClaw](/tools/aiming-lab-metaclaw.md) | [LLM-Agent-Paper-List](/tools/woooodyy-llm-agent-paper-list.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Dormant (18%) | | Days since push | 104d | 371d | | Open issues (now) | 17 | 32 | | Stars delta | +21 (30d) | +50 (30d) | | Open issues delta | 0 (30d) | +1 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/aiming-lab-metaclaw/trust.md) | [trust report](/tools/woooodyy-llm-agent-paper-list/trust.md) | ## Decision facts: MetaClaw - **Adopt for:** MetaClaw enables AI agents to evolve through continuous learning and interaction. ## Decision facts: LLM-Agent-Paper-List - **Adopt for:** LLM-Agent-Paper-List is a curated repository of essential papers on large language model-based agents, focusing on AgentGym, a framework for developing and training LLM agents through reinforcement learning. ## Choose when ### Choose MetaClaw if… - Tags unique to MetaClaw: ai-agent, continual-learning, fine-tuning, lora. - Need an agent that evolves and fine-tunes over time with user interactions. - More recently updated (last pushed Jun 7, 2026). ### Choose LLM-Agent-Paper-List if… - Tags unique to LLM-Agent-Paper-List: evaluation, large-language-models, nlp, reinforcement learning. - Also covers Evaluation & Observability. - When you need a comprehensive list of must-read papers on LLM-based agents, including detailed insights into AgentGym, a framework for developing and training LLM agents through reinforcement learning ## When NOT to use MetaClaw - Avoid if you need static models without evolving capabilities based on new data. - Not suitable for scenarios requiring immediate model stability post-training, as continuous updates can vary results. ## When NOT to use LLM-Agent-Paper-List - If you are looking for a tool that focuses on a broader range of AI agent development beyond LLM-based agents, as LLM-Agent-Paper-List is specifically curated for LLM-based agents - When you need real-time updates or a dynamic list of papers, as the repository is a static list and does not automatically update with new publications - If you require a tool that includes practical code implementations for all listed papers, as the repository primarily serves as a list and does not provide comprehensive code for every paper ## Common questions ### What is the difference between MetaClaw and LLM-Agent-Paper-List? MetaClaw: Simply converse with your agent, it learns and evolves. LLM-Agent-Paper-List: Must-read papers for LLM-based agents.. See the comparison table for live GitHub stats and shared categories. ### When should I choose MetaClaw over LLM-Agent-Paper-List? Choose MetaClaw over LLM-Agent-Paper-List when Tags unique to MetaClaw: ai-agent, continual-learning, fine-tuning, lora; Need an agent that evolves and fine-tunes over time with user interactions; More recently updated (last pushed Jun 7, 2026). ### When should I choose LLM-Agent-Paper-List over MetaClaw? Choose LLM-Agent-Paper-List over MetaClaw when Tags unique to LLM-Agent-Paper-List: evaluation, large-language-models, nlp, reinforcement learning; Also covers Evaluation & Observability; When you need a comprehensive list of must-read papers on LLM-based agents, including detailed insights into AgentGym, a framework for developing and training LLM agents through reinforcement learning. ### When should I avoid MetaClaw? Avoid if you need static models without evolving capabilities based on new data. Not suitable for scenarios requiring immediate model stability post-training, as continuous updates can vary results. ### When should I avoid LLM-Agent-Paper-List? If you are looking for a tool that focuses on a broader range of AI agent development beyond LLM-based agents, as LLM-Agent-Paper-List is specifically curated for LLM-based agents When you need real-time updates or a dynamic list of papers, as the repository is a static list and does not automatically update with new publications If you require a tool that includes practical code implementations for all listed papers, as the repository primarily serves as a list and does not provide comprehensive code for every paper ### Is MetaClaw or LLM-Agent-Paper-List more popular on GitHub? LLM-Agent-Paper-List has more GitHub stars (8,222 vs 3,493). Stars measure visibility, not whether either tool fits your constraints. ### Are MetaClaw and LLM-Agent-Paper-List open source? Yes - both are open-source projects on GitHub. ### Where can I find alternatives to MetaClaw or LLM-Agent-Paper-List? GraphCanon lists graph-backed alternatives at [MetaClaw alternatives](/tools/aiming-lab-metaclaw/alternatives) and [LLM-Agent-Paper-List alternatives](/tools/woooodyy-llm-agent-paper-list/alternatives) ([MetaClaw markdown twin](/tools/aiming-lab-metaclaw/alternatives.md), [LLM-Agent-Paper-List markdown twin](/tools/woooodyy-llm-agent-paper-list/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/aiming-lab-metaclaw-vs-woooodyy-llm-agent-paper-list.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, MetaClaw or LLM-Agent-Paper-List? MetaClaw: Slowing. LLM-Agent-Paper-List: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for MetaClaw and LLM-Agent-Paper-List? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [MetaClaw trust report](/tools/aiming-lab-metaclaw/trust); [LLM-Agent-Paper-List trust report](/tools/woooodyy-llm-agent-paper-list/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=aiming-lab-metaclaw`](/api/graphcanon/graph?tool=aiming-lab-metaclaw) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_