m2m-vector-search

Edge Vector search engine with Vulkan GPU acceleration, hierarchical indexing (HRM2), and native LangChain integration. Gaussian…

A new way for AI to search for data

View on GitHub

23GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 90734e96c6 (2026-10-10).

Selected work

Brian Schwabauer
@schwabauerbriantomas-gif

“SQ8DiskStore: modo comprimido opt-in (H13)”. 4 files, 408 lines in src/m2m, bench, tests.

Licence

The repository

AGPL-3.0

Checked by a person at the pinned commit.

The XERJ corpus

Approach only

The author agreed by email on 2026-10-12. Agents read it for how it works, not to copy it. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: approach only

edge-computingembeddingsgaussian-splattinggpu-computinglangchainllamaindexlocal-firstpython

Example questions

How does m2m-vector-search implement edge-computing?
Where does m2m-vector-search handle “SQ8DiskStore: modo comprimido opt-in (H13)”?
What does src/m2m do in m2m-vector-search?

The prompt

Paste it into your AI agent. It clones schwabauerbriantomas-gif/m2m-vector-search at the pinned commit and indexes it on your machine.

Search the GitHub repository schwabauerbriantomas-gif/m2m-vector-search with XERJ (https://hub.xerj.org/corpus/schwabauerbriantomas-gif--m2m-vector-search).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/schwabauerbriantomas-gif/m2m-vector-search m2m-vector-search && git -C m2m-vector-search checkout 90734e96c6f34a405d56c701dfcd9725a479f514
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./m2m-vector-search --url http://127.0.0.1:9200 --prefix m2m-vector-search --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: AGPL-3.0. Read it for the approach only, do not copy code.

Brian Schwabauer Databases and storage engines corpora icd10-who adalflow gpt-engineer tejas-parjane/business-intelligent-rag-agent muzakkirhussain011/needtoknow SheikhSarvar/pyrag-core

Selected work and consent: the XERJ registry.