markdown-memory
PulseGate's liveness check found it on 30 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 30 Sep 2026. How this is checked
markdown-memory is an open-source MCP server that indexes Markdown files and returns the most relevant sections to coding agents. It combines BM25 keyword search with local ONNX embeddings in SQLite, requiring no API keys or network access.
Inferred · not functionally tested
Overview
6 featuresPurpose: Finding the relevant documentation section for coding-agent questions without sending files to a remote service.
Inferred · not functionally tested
Audience: developers building or using coding agents
Inferred · not functionally tested
Functions: rag, data_extraction
Inferred · not functionally tested
Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: pypi.org · github.com. These links do not verify the individual claims.
markdown-memory is a RAG, search & retrieval project. Inferred · not functionally tested: It focuses on finding the relevant documentation section for coding-agent questions without sending files to a remote service. Inferred · not functionally tested: It is built as an open-source project for developers building or using coding agents. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It ships for the command line, and it can be self-hosted.
It is developed by Hisham Karam, and it first shipped in 2026. Development happens publicly on GitHub with 38 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are markdown indexing, hybrid search, and BM25 search. Basis unknown · not verified: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Markdown indexing
- Hybrid search
- BM25 search
- ONNX embeddings
- SQLite storage
- Semantic search
Topics: Inferred · not functionally tested
Built with & integrations
- Claude Code
- .claude/
- Cursor
- .cursorrules
Trust & compliance
Indexing history
19What PulseGate has recorded for this listing
- Indexed30 Sep · 03:43 UTCmarkdown-memory seen via PyPI Bulk EnumeratorSource: PyPI Bulk Enumerator · Open
Frequently asked questions about markdown-memory
- What does markdown-memory do?
- Inferred · not functionally tested: Markdown-memory focuses on finding the relevant documentation section for coding-agent questions without sending files to a remote service. It is catalogued under RAG, search & retrieval on PulseGate.
- Who is markdown-memory for?
- Inferred · not functionally tested: markdown-memory is an open-source project built for developers building or using coding agents.
- Is markdown-memory free?
- Basis unknown · not verified: Yes — markdown-memory is open source under the MIT license and free to use.
- What platforms does markdown-memory run on?
- Basis unknown · not verified: markdown-memory runs on the command line. It can also be self-hosted.
- Is markdown-memory still maintained?
- PulseGate's liveness check found it on 30 Sep 2026. Its GitHub repository shows 38 commits in the last 90 days.
- What are alternatives to markdown-memory?
- Similar projects tracked by PulseGate include memory-boost, memtomem, and memo.memory-boostmemtomemmemo
- Who develops markdown-memory?
- markdown-memory is developed by Hisham Karam.
- How long has markdown-memory been around?
- markdown-memory first shipped in 2026.
Similar projects
Closest matches by what these projects do