--- title: "dust vs agentflow" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/dust-tt-dust-vs-simonmesmith-agentflow" tools: ["dust-tt-dust", "simonmesmith-agentflow"] --- # dust vs agentflow *GraphCanon updated Aug 16, 2026* ## Verdict Pick dust if dust, a TypeScript and Rust-based AI agent platform for workflow acceleration; pick agentflow if agentflow simplifies the creation of complex workflows for large language models through simple JSON configurations. [dust](https://dust.tt) reports 1.4k GitHub stars, 329 forks, and 315 open issues, last pushed Aug 15, 2026. [agentflow](https://github.com/simonmesmith/agentflow) has 320 stars, 27 forks, and 13 open issues, last pushed Aug 11, 2023. Figures are from public GitHub metadata via [dust's repository](https://github.com/dust-tt/dust) and [agentflow's repository](https://github.com/simonmesmith/agentflow). | | [dust](/tools/dust-tt-dust.md) | [agentflow](/tools/simonmesmith-agentflow.md) | | --- | --- | --- | | Tagline | Custom AI agent platform to speed up your work. | Complex LLM Workflows from Simple JSON | | Stars | 1,438 | 320 | | Forks | 329 | 27 | | Open issues | 315 | 13 | | Language | TypeScript | Python | | Adopt for | Dust, a TypeScript and Rust-based AI agent platform for workflow acceleration. | Agentflow simplifies the creation of complex workflows for large language models through simple JSON configurations. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | AI Agents | AI Agents, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [dust](/tools/dust-tt-dust.md) | [agentflow](/tools/simonmesmith-agentflow.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Dormant (18%) | | Days since push | 0d | 1100d | | Open issues (now) | 315 | 13 | | Stars delta | +23 (30d) | -1 (30d) | | Open issues delta | +68 (30d) | 0 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/dust-tt-dust/trust.md) | [trust report](/tools/simonmesmith-agentflow/trust.md) | ## Decision facts: dust - **Adopt for:** Dust, a TypeScript and Rust-based AI agent platform for workflow acceleration. ## Decision facts: agentflow - **Adopt for:** Agentflow simplifies the creation of complex workflows for large language models through simple JSON configurations. ## Choose when ### Choose dust if… - dust is primarily TypeScript; agentflow is Python. - Tags unique to dust: agents, llm, rust. - dust ships Docker support for self-hosted deployment. - Need customization in AI agents with TypeScript and Rust support ### Choose agentflow if… - agentflow is primarily Python; dust is TypeScript. - Tags unique to agentflow: json, python, workflow-management. - Also covers LLM Frameworks. - When you need to rapidly prototype LLM workflows with minimal coding via JSON configs ## When NOT to use dust - Prefer fully managed AI services without needing low-level tuning options - Require integration with frameworks that do not support TypeScript or Rust ## When NOT to use agentflow - Avoid if requiring advanced customization that goes beyond basic JSON configurations - Not suitable for scenarios needing real-time dynamic changes in workflow setup during execution ## Common questions ### What is the difference between dust and agentflow? dust: Custom AI agent platform to speed up your work.. agentflow: Complex LLM Workflows from Simple JSON. See the comparison table for live GitHub stats and shared categories. ### When should I choose dust over agentflow? Choose dust over agentflow when dust is primarily TypeScript; agentflow is Python; Tags unique to dust: agents, llm, rust; dust ships Docker support for self-hosted deployment; Need customization in AI agents with TypeScript and Rust support. ### When should I choose agentflow over dust? Choose agentflow over dust when agentflow is primarily Python; dust is TypeScript; Tags unique to agentflow: json, python, workflow-management; Also covers LLM Frameworks; When you need to rapidly prototype LLM workflows with minimal coding via JSON configs. ### When should I avoid dust? Prefer fully managed AI services without needing low-level tuning options Require integration with frameworks that do not support TypeScript or Rust ### When should I avoid agentflow? Avoid if requiring advanced customization that goes beyond basic JSON configurations Not suitable for scenarios needing real-time dynamic changes in workflow setup during execution ### Is dust or agentflow more popular on GitHub? dust has more GitHub stars (1,438 vs 320). Stars measure visibility, not whether either tool fits your constraints. ### Are dust and agentflow open source? Yes - both are open-source projects on GitHub (dust: MIT, agentflow: MIT). ### Where can I find alternatives to dust or agentflow? GraphCanon lists graph-backed alternatives at [dust alternatives](/tools/dust-tt-dust/alternatives) and [agentflow alternatives](/tools/simonmesmith-agentflow/alternatives) ([dust markdown twin](/tools/dust-tt-dust/alternatives.md), [agentflow markdown twin](/tools/simonmesmith-agentflow/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/dust-tt-dust-vs-simonmesmith-agentflow.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, dust or agentflow? dust: Very active. 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 dust and agentflow? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [dust trust report](/tools/dust-tt-dust/trust); [agentflow trust report](/tools/simonmesmith-agentflow/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=dust-tt-dust`](/api/graphcanon/graph?tool=dust-tt-dust) - 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/_