head to head · open source

PageIndex vs mcp-memory-service

PageIndex has 39,973 GitHub stars, 3,442 forks, 103 open issues and last shipped 2 days ago. mcp-memory-service has 2,073 stars, 386 forks, 30 open issues and last shipped yesterday. PageIndex leads on adoption by 1,828% (39,973 vs 2,073 stars). PageIndex is written in Python under MIT; mcp-memory-service is written in Python under Apache-2.0. PageIndex has attracted 9% as many forks as stars, mcp-memory-service 19%. mcp-memory-service was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (agentic-ai, ai-agents), so they are genuine substitutes rather than adjacent tools.

Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.

PageIndex ★ 40K mcp-memory-service ★ 2.1K category AI & Machine Learning

← all 20902 open source comparisons

Side by side

PageIndex mcp-memory-service
GitHub stars ★ 40K ★ 2.1K
License MIT Apache-2.0
Written in Python Python
Last push 2026-11-03 2026-11-04
Forks ⑂ 3.4K ⑂ 386
Self-hosting Yes Yes
Data ownership Your server Your server

pick PageIndex if

  • You weight community size — 40K stars and counting
  • You want the MIT license terms
  • Your stack matches Python
  • You value the larger contributor base for long-term maintenance

full PageIndex profile →

pick mcp-memory-service if

  • You want the mcp-memory-service feature set and don't need the biggest community
  • You prefer the Apache-2.0 license terms
  • Your stack matches Python
  • You evaluated both and mcp-memory-service fits your workflow better

full mcp-memory-service profile →

About PageIndex

PageIndex: Vectorless, Reasoning based RAG Reasoning based RAG ◦ No Vector DB, No Chunking ◦ Context Aware Retrieval ◦ Reads Like a Human 🌐 Website • ☁️ Cloud • 📖 Docs • 📝 Blog • ✉️ Contact Updates [Aug '26] 🔥 PageIndex SDK : pip install U pageindex now ships local mode : index, retrieve, and chat entirely on your machine with your own LLM key, or point the same client at PageIndex Cloud with an API key. [Aug '26] ⚡ PageIndex Flash : fast tree index generation for text based PDFs, now the default indexing method in PageIndex SDK local mode. Scale PageIndex to Millions of Documents: PageIndex File System is a…

read the full PageIndex overview →

About mcp-memory-service

This repository has moved to GitHub Active development, issues, pull requests, CI and releases are at as of 5 September 2026. This copy stays here, readable and unchanged, so that existing links, issue numbers and pull request references keep resolving. It receives no further pushes and its CI no longer runs. Please do not open issues or pull requests here, they will not be seen. The wiki moved too: mcp memory service Persistent Shared Memory for AI Agent Pipelines Open source memory backend for AI agents — REST API, MCP, OAuth, CLI, dashboard . One self hosted service, every transport. Agents store decisions…

read the full mcp-memory-service overview →

More in AI & Machine Learning

Related comparisons

More Machine Learning Infrastructure projects

Compare either of these against the rest of the Machine Learning Infrastructure field.

Frequently asked questions

Is PageIndex or mcp-memory-service more popular?

PageIndex has 39,973 GitHub stars and mcp-memory-service has 2,073. PageIndex has the larger community by that measure.

Are PageIndex and mcp-memory-service free?

Both are open source. PageIndex is licensed under MIT and mcp-memory-service under Apache-2.0. Neither carries a licence fee.

What is the difference between PageIndex and mcp-memory-service?

PageIndex is written in Python and mcp-memory-service in Python. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.

Which should I choose, PageIndex or mcp-memory-service?

Choose PageIndex if you want the larger community (39,973 stars) or its MIT licence terms. Choose mcp-memory-service if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.