--- title: "SPPO vs agents" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/uclaml-sppo-vs-wshobson-agents" tools: ["uclaml-sppo", "wshobson-agents"] --- # SPPO vs agents *GraphCanon updated Jul 11, 2026* ## Verdict Pick SPPO when license: SPPO is Apache-2.0, agents is MIT; pick agents when license: agents is MIT, SPPO is Apache-2.0. [SPPO](https://uclaml.github.io/SPPO/) reports 589 GitHub stars, 48 forks, and 15 open issues, last pushed Jan 23, 2025. [agents](https://sethhobson.com) has 38k stars, 4.0k forks, and 1 open issues, last pushed Jul 8, 2026. Figures are from public GitHub metadata via [SPPO's repository](https://github.com/uclaml/SPPO) and [agents's repository](https://github.com/wshobson/agents). | | [SPPO](/tools/uclaml-sppo.md) | [agents](/tools/wshobson-agents.md) | | --- | --- | --- | | Tagline | The official implementation of Self-Play Preference Optimization (SPPO) | Multi-harness agentic plugin marketplace for various AI agents | | Stars | 589 | 37,779 | | Forks | 48 | 4,050 | | Open issues | 15 | 1 | | Language | Python | Python | | Adopt for | - | The agents tool is a marketplace for plugins that enhances multiple AI agents, offering integration and management capabilities across several platforms, including Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT | | Categories | Developer Tools | AI Agents, Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [SPPO](/tools/uclaml-sppo.md) | [agents](/tools/wshobson-agents.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Very active (96%) | | Days since push | 534d | 2d | | Open issues (now) | 15 | 1 | | Security scan | No lockfile | No MCP manifest | | Full report | [trust report](/tools/uclaml-sppo/trust.md) | [trust report](/tools/wshobson-agents/trust.md) | ## Decision facts: agents - **Adopt for:** The agents tool is a marketplace for plugins that enhances multiple AI agents, offering integration and management capabilities across several platforms, including Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot ## Choose when ### Choose SPPO if… - License: SPPO is Apache-2.0, agents is MIT. - Tags unique to SPPO: deep-learning, fine-tuning, large-language-models, python. ### Choose agents if… - License: agents is MIT, SPPO is Apache-2.0. - Tags unique to agents: agent-skills, agentic-ai, automation, prompt-engineering. - Also covers AI Agents. - You are working specifically within the ecosystems of Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, or Gemini CLI, as it provides tailored plugins for these environments ## When NOT to use SPPO - Last GitHub push was 535 days ago (dormant maintenance, Jan 23, 2025). Validate activity before betting a new project on SPPO. - Developer Tools: A gateway is overkill when you're pinned to a single provider and model. ## When NOT to use agents - You are working solely within a niche environment that isn't one of the supported platforms (like Claude Code, Codex CLI, etc.) because it may not offer compatible plugins or extensive support - Your project requirements do not include interoperability between multiple AI agents and you only need to leverage functionalities from a single AI agent with a robust in-built plugin ecosystem ## Common questions ### What is the difference between SPPO and agents? SPPO: The official implementation of Self-Play Preference Optimization (SPPO). agents: Multi-harness agentic plugin marketplace for various AI agents. See the comparison table for live GitHub stats and shared categories. ### When should I choose SPPO over agents? Choose SPPO over agents when License: SPPO is Apache-2.0, agents is MIT; Tags unique to SPPO: deep-learning, fine-tuning, large-language-models, python. ### When should I choose agents over SPPO? Choose agents over SPPO when License: agents is MIT, SPPO is Apache-2.0; Tags unique to agents: agent-skills, agentic-ai, automation, prompt-engineering; Also covers AI Agents; You are working specifically within the ecosystems of Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, or Gemini CLI, as it provides tailored plugins for these environments. ### When should I avoid SPPO? Last GitHub push was 535 days ago (dormant maintenance, Jan 23, 2025). Validate activity before betting a new project on SPPO. Developer Tools: A gateway is overkill when you're pinned to a single provider and model. ### When should I avoid agents? You are working solely within a niche environment that isn't one of the supported platforms (like Claude Code, Codex CLI, etc.) because it may not offer compatible plugins or extensive support Your project requirements do not include interoperability between multiple AI agents and you only need to leverage functionalities from a single AI agent with a robust in-built plugin ecosystem ### Is SPPO or agents more popular on GitHub? agents has more GitHub stars (37,779 vs 589). Stars measure visibility, not whether either tool fits your constraints. ### Are SPPO and agents open source? Yes - both are open-source projects on GitHub (SPPO: Apache-2.0, agents: MIT). ### Where can I find alternatives to SPPO or agents? GraphCanon lists graph-backed alternatives at [SPPO alternatives](/tools/uclaml-sppo/alternatives) and [agents alternatives](/tools/wshobson-agents/alternatives) ([SPPO markdown twin](/tools/uclaml-sppo/alternatives.md), [agents markdown twin](/tools/wshobson-agents/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/uclaml-sppo-vs-wshobson-agents.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, SPPO or agents? SPPO: Dormant. agents: Very active. 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 SPPO and agents? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [SPPO trust report](/tools/uclaml-sppo/trust); [agents trust report](/tools/wshobson-agents/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=uclaml-sppo`](/api/graphcanon/graph?tool=uclaml-sppo) - 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/_