--- title: "comfyui_LLM_party vs open-dungeon" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/heshengtao-comfyui-llm-party-vs-newideas99-open-dungeon" tools: ["heshengtao-comfyui-llm-party", "newideas99-open-dungeon"] --- # comfyui_LLM_party vs open-dungeon *GraphCanon updated Sep 20, 2026* ## Verdict Pick comfyui_LLM_party if comfyUI_LLM_party: A Python-based agent framework adapted for LLMs like Qwen, GLM, Gemini, and local models including llama-3.3, Janus-Pro; pick open-dungeon if open Dungeon stands out with its emphasis on full local processing of both text and image generation, utilizing Gemma 4 QAT via Ollama for interactive-fiction roleplaying experiences. [comfyui_LLM_party](https://github.com/heshengtao/comfyui_LLM_party) reports 2.4k GitHub stars, 206 forks, and 87 open issues, last pushed Jul 29, 2026. [open-dungeon](https://github.com/newideas99/open-dungeon) has 228 stars, 22 forks, and 1 open issues, last pushed Jul 6, 2026. Figures are from public GitHub metadata via [comfyui_LLM_party's repository](https://github.com/heshengtao/comfyui_LLM_party) and [open-dungeon's repository](https://github.com/newideas99/open-dungeon). | | [comfyui_LLM_party](/tools/heshengtao-comfyui-llm-party.md) | [open-dungeon](/tools/newideas99-open-dungeon.md) | | --- | --- | --- | | Tagline | LLM Agent Framework in ComfyUI with various nodes and adapters for different LLMs and VLMs | easy-to-use fully local AI roleplay app with story and inline scene images generated on your machine | | Stars | 2,361 | 228 | | Forks | 206 | 22 | | Open issues | 87 | 1 | | Language | Python | TypeScript | | Adopt for | ComfyUI_LLM_party: A Python-based agent framework adapted for LLMs like Qwen, GLM, Gemini, and local models including llama-3.3, Janus-Pro. | Open Dungeon stands out with its emphasis on full local processing of both text and image generation, utilizing Gemma 4 QAT via Ollama for interactive-fiction roleplaying experiences. | | Persona | - | - | | Runtime | - | - | | License | AGPL-3.0 | MIT | | Categories | Data & Retrieval, Inference & Serving, LLM Frameworks, Model Training | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [comfyui_LLM_party](/tools/heshengtao-comfyui-llm-party.md) | [open-dungeon](/tools/newideas99-open-dungeon.md) | | --- | --- | --- | | Days since push | 49d | 76d | | Open issues (now) | 87 | 1 | | Stars delta | +31 (30d) | +16 (30d) | | Open issues delta | +9 (30d) | +1 (30d) | | Full report | [trust report](/tools/heshengtao-comfyui-llm-party/trust.md) | [trust report](/tools/newideas99-open-dungeon/trust.md) | ## Decision facts: comfyui_LLM_party - **Requirements:** The project requires patience and thorough reading due to its high usage threshold - **Adopt for:** ComfyUI_LLM_party: A Python-based agent framework adapted for LLMs like Qwen, GLM, Gemini, and local models including llama-3.3, Janus-Pro. - **License detail:** AGPL-3.0 ## Decision facts: open-dungeon - **Adopt for:** Open Dungeon stands out with its emphasis on full local processing of both text and image generation, utilizing Gemma 4 QAT via Ollama for interactive-fiction roleplaying experiences. ## Choose when ### Choose comfyui_LLM_party if… - comfyui_LLM_party is primarily Python; open-dungeon is TypeScript. - License: comfyui_LLM_party is AGPL-3.0, open-dungeon is MIT. - Requirements: The project requires patience and thorough reading due to its high usage threshold. - Tags unique to comfyui_LLM_party: agent, comfyui, dify, flux. - Also covers Data & Retrieval, Inference & Serving. - - When you need to work with multiple Large Language Models using the ComfyUI interface ### Choose open-dungeon if… - open-dungeon is primarily TypeScript; comfyui_LLM_party is Python. - License: open-dungeon is MIT, comfyui_LLM_party is AGPL-3.0. - Tags unique to open-dungeon: image-generation, interactive-fiction, local-llm, on-device-ai. - When you need to generate roleplay stories and inline scene images entirely offline without relying on any cloud services or API keys ## When NOT to use comfyui_LLM_party - - Avoid if your primary environment is not Windows, as some portable packages are exclusively for this OS - - Not recommended if you require specific features or support that is exclusive to a particular competitor's framework ## When NOT to use open-dungeon - When you rely on continuous model updates delivered via the cloud since Open Dungeon processes everything locally and does not connect for updates - If your preferred environment is web-based with real-time collaboration features as Open Dungeon focuses purely on local execution, lacking online connectivity altogether ## Common questions ### What is the difference between comfyui_LLM_party and open-dungeon? comfyui_LLM_party: LLM Agent Framework in ComfyUI with various nodes and adapters for different LLMs and VLMs. open-dungeon: easy-to-use fully local AI roleplay app with story and inline scene images generated on your machine. See the comparison table for live GitHub stats and shared categories. ### When should I choose comfyui_LLM_party over open-dungeon? Choose comfyui_LLM_party over open-dungeon when comfyui_LLM_party is primarily Python; open-dungeon is TypeScript; License: comfyui_LLM_party is AGPL-3.0, open-dungeon is MIT; Requirements: The project requires patience and thorough reading due to its high usage threshold; Tags unique to comfyui_LLM_party: agent, comfyui, dify, flux; Also covers Data & Retrieval, Inference & Serving; - When you need to work with multiple Large Language Models using the ComfyUI interface. ### When should I choose open-dungeon over comfyui_LLM_party? Choose open-dungeon over comfyui_LLM_party when open-dungeon is primarily TypeScript; comfyui_LLM_party is Python; License: open-dungeon is MIT, comfyui_LLM_party is AGPL-3.0; Tags unique to open-dungeon: image-generation, interactive-fiction, local-llm, on-device-ai; When you need to generate roleplay stories and inline scene images entirely offline without relying on any cloud services or API keys. ### When should I avoid comfyui_LLM_party? - Avoid if your primary environment is not Windows, as some portable packages are exclusively for this OS - Not recommended if you require specific features or support that is exclusive to a particular competitor's framework ### When should I avoid open-dungeon? When you rely on continuous model updates delivered via the cloud since Open Dungeon processes everything locally and does not connect for updates If your preferred environment is web-based with real-time collaboration features as Open Dungeon focuses purely on local execution, lacking online connectivity altogether ### Is comfyui_LLM_party or open-dungeon more popular on GitHub? comfyui_LLM_party has more GitHub stars (2,361 vs 228). Stars measure visibility, not whether either tool fits your constraints. ### Are comfyui_LLM_party and open-dungeon open source? Yes - both are open-source projects on GitHub (comfyui_LLM_party: AGPL-3.0, open-dungeon: MIT). ### Where can I find alternatives to comfyui_LLM_party or open-dungeon? GraphCanon lists graph-backed alternatives at [comfyui_LLM_party alternatives](/tools/heshengtao-comfyui-llm-party/alternatives) and [open-dungeon alternatives](/tools/newideas99-open-dungeon/alternatives) ([comfyui_LLM_party markdown twin](/tools/heshengtao-comfyui-llm-party/alternatives.md), [open-dungeon markdown twin](/tools/newideas99-open-dungeon/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/heshengtao-comfyui-llm-party-vs-newideas99-open-dungeon.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, comfyui_LLM_party or open-dungeon? comfyui_LLM_party: Steady. open-dungeon: Steady. 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 comfyui_LLM_party and open-dungeon? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [comfyui_LLM_party trust report](/tools/heshengtao-comfyui-llm-party/trust); [open-dungeon trust report](/tools/newideas99-open-dungeon/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=heshengtao-comfyui-llm-party`](/api/graphcanon/graph?tool=heshengtao-comfyui-llm-party) - 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/_