--- title: "coca vs agents" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/phodal-coca-vs-wshobson-agents" tools: ["phodal-coca", "wshobson-agents"] --- # coca vs agents *GraphCanon updated Jul 15, 2026* ## Verdict Pick coca when coca is primarily Go; agents is Python; pick agents when agents is primarily Python; coca is Go. [coca](https://coca.migration.ink/) reports 989 GitHub stars, 117 forks, and 0 open issues, last pushed Jan 6, 2026. [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 [coca's repository](https://github.com/phodal/coca) and [agents's repository](https://github.com/wshobson/agents). | | [coca](/tools/phodal-coca.md) | [agents](/tools/wshobson-agents.md) | | --- | --- | --- | | Tagline | Coca is a toolbox which is design for legacy system refactoring and analysis, includes call graph, concept analysis, api tree, design patterns suggest. Coca 是一个用于系统重构、系统迁移和系统分析的工具箱。它可以分析代码中的测试坏味道、模块化分 | Multi-harness agentic plugin marketplace for various AI agents | | Stars | 989 | 37,779 | | Forks | 117 | 4,050 | | Open issues | 0 | 1 | | Language | Go | 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 | MPL-2.0 | MIT | | Categories | Developer Tools | AI Agents, Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [coca](/tools/phodal-coca.md) | [agents](/tools/wshobson-agents.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Very active (96%) | | Days since push | 190d | 2d | | Open issues (now) | 0 | 1 | | Full report | [trust report](/tools/phodal-coca/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 coca if… - coca is primarily Go; agents is Python. - License: coca is MPL-2.0, agents is MIT. - Tags unique to coca: ai, architecture, git, go. ### Choose agents if… - agents is primarily Python; coca is Go. - License: agents is MIT, coca is MPL-2.0. - Tags unique to agents: agent-skills, agentic-ai, prompt-engineering, workflows. - 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 coca - Last GitHub push was 190 days ago (slowing maintenance, Jan 6, 2026). Validate activity before betting a new project on coca. - 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 coca and agents? coca: Coca is a toolbox which is design for legacy system refactoring and analysis, includes call graph, concept analysis, api tree, design patterns suggest. Coca 是一个用于系统重构、系统迁移和系统分析的工具箱。它可以分析代码中的测试坏味道、模块化分. 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 coca over agents? Choose coca over agents when coca is primarily Go; agents is Python; License: coca is MPL-2.0, agents is MIT; Tags unique to coca: ai, architecture, git, go. ### When should I choose agents over coca? Choose agents over coca when agents is primarily Python; coca is Go; License: agents is MIT, coca is MPL-2.0; Tags unique to agents: agent-skills, agentic-ai, prompt-engineering, workflows; 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 coca? Last GitHub push was 190 days ago (slowing maintenance, Jan 6, 2026). Validate activity before betting a new project on coca. 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 coca or agents more popular on GitHub? agents has more GitHub stars (37,779 vs 989). Stars measure visibility, not whether either tool fits your constraints. ### Are coca and agents open source? Yes - both are open-source projects on GitHub (coca: MPL-2.0, agents: MIT). ### Where can I find alternatives to coca or agents? GraphCanon lists graph-backed alternatives at [coca alternatives](/tools/phodal-coca/alternatives) and [agents alternatives](/tools/wshobson-agents/alternatives) ([coca markdown twin](/tools/phodal-coca/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/phodal-coca-vs-wshobson-agents.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, coca or agents? coca: Slowing. 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 coca and agents? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [coca trust report](/tools/phodal-coca/trust); [agents trust report](/tools/wshobson-agents/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=phodal-coca`](/api/graphcanon/graph?tool=phodal-coca) - 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/_