Comparison
open-dungeon vs agentflow
Verdict
Unverified catalog guidance: open-dungeon: 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. agentflow: Agentflow simplifies the creation of complex workflows for large language models through simple JSON configurations.
Markdown twin · open-dungeon alternatives · agentflow alternatives
GraphCanon updated Sep 20, 2026
Trust & integrity
| Signal | open-dungeon | agentflow |
|---|---|---|
| Maintenance | Steady (76d since push) As of Sep 20, 2026 · github_public_v1 | Dormant (1100d since push) As of Aug 16, 2026 · github_public_v1 |
| Provenance | Not a fork · Personal account As of Sep 20, 2026 · github_public_v1 | Not a fork · Personal account As of Aug 16, 2026 · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of Jul 15, 2026 · osv@v1 | No lockfile (source not queried) As of Jul 11, 2026 · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- open-dungeon
- easy-to-use fully local AI roleplay app with story and inline scene images generated on your machine
- agentflow
- Complex LLM Workflows from Simple JSON
Stars
- open-dungeon
- 228
- agentflow
- 320
Forks
- open-dungeon
- 22
- agentflow
- 27
Open issues
- open-dungeon
- 1
- agentflow
- 13
Language
- open-dungeon
- TypeScript
- agentflow
- Python
Adopt for
- open-dungeon
- Unverified catalog guidance: 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.
- agentflow
- Unverified catalog guidance: Agentflow simplifies the creation of complex workflows for large language models through simple JSON configurations.
Persona
- open-dungeon
- -
- agentflow
- -
Runtime
- open-dungeon
- -
- agentflow
- -
License
- open-dungeon
- MIT
- agentflow
- MIT
Last pushed
- open-dungeon
- Jul 6, 2026
- agentflow
- Aug 11, 2023
Categories
- open-dungeon
- LLM Frameworks, Model Training
- agentflow
- AI Agents, LLM Frameworks
Trust and health
Maintenance
- open-dungeon
- Steady (60%)
- agentflow
- Dormant (18%)
Days since push
- open-dungeon
- 76d
- agentflow
- 1100d
Open issues (recorded)
- open-dungeon
- 1
- agentflow
- 13
Stars delta
- open-dungeon
- +16 (30d)
- agentflow
- -1 (30d)
Open issues delta
- open-dungeon
- +1 (30d)
- agentflow
- 0 (30d)
Full report
- open-dungeon
- Trust report
- agentflow
- Trust report
Choose open-dungeon if…
- open-dungeon is primarily TypeScript; agentflow is Python.
- Tags unique to open-dungeon: image-generation, interactive-fiction, local-llm, on-device-ai.
- Also covers Model Training.
- Unverified catalog guidance: 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 open-dungeon
- Unverified catalog guidance: When you rely on continuous model updates delivered via the cloud since Open Dungeon processes everything locally and does not connect for updates
- Unverified catalog guidance: If your preferred environment is web-based with real-time collaboration features as Open Dungeon focuses purely on local execution, lacking online connectivity altogether
Choose agentflow if…
- agentflow is primarily Python; open-dungeon is TypeScript.
- Tags unique to agentflow: json, large-language-models, python, workflow-management.
- Also covers AI Agents.
- Unverified catalog guidance: When you need to rapidly prototype LLM workflows with minimal coding via JSON configs
When NOT to use agentflow
- Unverified catalog guidance: Avoid if requiring advanced customization that goes beyond basic JSON configurations
- Unverified catalog guidance: Not suitable for scenarios needing real-time dynamic changes in workflow setup during execution
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (newideas99/open-dungeon) · observed Sep 20, 2026
- GitHub forks (newideas99/open-dungeon) · observed Sep 20, 2026
- Last push (newideas99/open-dungeon) · observed Jul 6, 2026
- License file (MIT) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 15, 2026
- GitHub stars (simonmesmith/agentflow) · observed Sep 20, 2026
- GitHub forks (simonmesmith/agentflow) · observed Sep 20, 2026
- Last push (simonmesmith/agentflow) · observed Aug 11, 2023
- License file (MIT) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: open-dungeon 228 · agentflow 320 (synced Sep 20, 2026).
Common questions
- What is the difference between open-dungeon and agentflow?
- open-dungeon: easy-to-use fully local AI roleplay app with story and inline scene images generated on your machine. agentflow: Complex LLM Workflows from Simple JSON. See the comparison table for recorded GitHub metadata and shared categories.
- When should I choose open-dungeon over agentflow?
- For open-dungeon, compare these recorded points with agentflow: open-dungeon is primarily TypeScript; agentflow is Python; Tags unique to open-dungeon: image-generation, interactive-fiction, local-llm, on-device-ai; Also covers Model Training; Unverified catalog guidance: 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 choose agentflow over open-dungeon?
- For agentflow, compare these recorded points with open-dungeon: agentflow is primarily Python; open-dungeon is TypeScript; Tags unique to agentflow: json, large-language-models, python, workflow-management; Also covers AI Agents; Unverified catalog guidance: When you need to rapidly prototype LLM workflows with minimal coding via JSON configs.
- When should I avoid open-dungeon?
- Unverified catalog guidance: When you rely on continuous model updates delivered via the cloud since Open Dungeon processes everything locally and does not connect for updates Unverified catalog guidance: If your preferred environment is web-based with real-time collaboration features as Open Dungeon focuses purely on local execution, lacking online connectivity altogether
- When should I avoid agentflow?
- Unverified catalog guidance: Avoid if requiring advanced customization that goes beyond basic JSON configurations Unverified catalog guidance: Not suitable for scenarios needing real-time dynamic changes in workflow setup during execution
- Is open-dungeon or agentflow more popular on GitHub?
- agentflow has more recorded GitHub stars (320 vs 228). Stars measure visibility, not whether either tool fits your constraints.
- Which licenses are recorded for open-dungeon and agentflow?
- open-dungeon: MIT. agentflow: MIT. Check each repository's current license and terms before use. Public GitHub hosting alone does not establish open-source licensing.
- Where can I find alternatives to open-dungeon or agentflow?
- GraphCanon lists candidates at open-dungeon alternatives and agentflow alternatives (open-dungeon markdown twin, agentflow markdown twin). The discovery order uses stored relationship proposals and shared categories; it is not a verified replacement ranking.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, open-dungeon or agentflow?
- open-dungeon: Steady. agentflow: 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 open-dungeon and agentflow?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: open-dungeon trust report; agentflow trust report.