ppt-master vs mastra
Two of the top projects in Agent frameworks and SDKs, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
ppt-master
Agent skill that turns documents into natively editable PowerPoint decks
mastra
TypeScript framework for building AI agents, workflows and MCP servers
Verdict
ppt-master ranks higher, 95 to 91. Of the 4 score parts we measure for both, ppt-master leads on 2, mastra on 1 and 1 is even.
- Adoptionppt-master leads by 15 points, 96 to 81: a wide gap.
- FreshnessEven at 100.
- Maintenanceppt-master leads by 5 points, 99 to 94.
- Agent-readymastra leads by 15 points, 85 to 70: a wide gap.
Pick ppt-master if you are
Users who want editable AI-generated PowerPoint decks from documents
- Exports native PowerPoint objects: shapes, charts, tables and slide masters stay editable
- Runs locally; only model, search, image and speech calls leave the machine
Pick mastra if you are
TypeScript developers building production agents and workflows
- Graph workflow engine with .then(), .branch() and .parallel() control flow
- Suspend and resume agents or workflows, with execution state kept in storage
| What we compare | ppt-master | mastra |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 96, widely used | 81, widely used |
| Momentum | Not scored for this kind | Not scored for this kind |
| Freshness | 100, active | 100, active |
| Maintenance | 99, healthy | 94, healthy |
| Agent-ready | 70, partly | 85, ready |
| Facts from GitHub and the README | ||
| Stars | 75.9k | 29.5k |
| License | MIT (permissive) | custom license (read the license) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | Nov 2026 |
| Language | Python | TypeScript |
| Docker | No | No |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Not stated | Not stated |
ppt-master
PPT Master is a workflow ("skill") that runs inside an agent-capable AI tool such as Claude Code, Cursor or Codex CLI. Given a PDF, DOCX, web page or topic, it plans the argument and exports a .pptx with native shapes, data-backed charts, tables and slide masters rather than images. It can also fill an existing .pptx, extract templates from references, and add transitions, animations and narration.
Who it is for: Users who want editable AI-generated PowerPoint decks from documents
Strengths
- Exports native PowerPoint objects: shapes, charts, tables and slide masters stay editable
- Runs locally; only model, search, image and speech calls leave the machine
- Works with any agent-capable tool and models like Claude, GPT, Gemini and Kimi
- Also fills existing .pptx files and adds transitions, animations and narration
Weaknesses
- Output quality depends on the driving model; cheaper models need more manual polish
- Needs a separate agent tool and model access; it is not a standalone app
- SmartArt is deliberately unsupported
- Recommended setup (~1M-token context model plus image generation API) adds usage cost
- no GPU
- Needs Python 3.10+, agent-capable AI tool (Claude Code, Cursor, Codex CLI, etc.), pandoc (only for legacy formats like .doc, .rtf), image generation API (optional)
- Models: Kimi K3, Claude, GPT, Gemini, gpt-image-2
mastra
Mastra is a TypeScript framework for building agents and graph-based workflows, with model routing across 40+ providers. It adds suspend/resume with stored state, memory, RAG, evals and observability, and runs inside React, Next.js or Node apps or as a standalone server. A local Studio on port 4111 is used to build and test agents, workflows and tools.
Who it is for: TypeScript developers building production agents and workflows
Strengths
- Graph workflow engine with .then(), .branch() and .parallel() control flow
- Suspend and resume agents or workflows, with execution state kept in storage
- Built-in evals, observability, memory and RAG alongside agents
- Can author MCP servers exposing agents and tools
Weaknesses
- TypeScript only; no other language SDKs mentioned
- Code in ee/ directories needs an enterprise license for production use
- Pull requests limited to collaborators
- No Docker or compose files in the repo
- no GPU
- Needs Node.js, LLM provider API key
- Models: OpenAI, Anthropic, Gemini, xAI, 40+ providers via model router
- port 4111
More in Agent frameworks and SDKs
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.