iMil

Corpus Hub contributor since 2026-10-16

iMil's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.

1corpus

1selected commit

6files

170lines

★ 774GitHub stars on repo

Totals across every corpus @iMilnb appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.

What an agent can do with the PolyStrata corpus

VecSzn/PolyStrata: Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith…

Look up how PolyStrata implements anthropic-api, cuda, gemma, with answers cited to file and line.
Reuse a worked example: the commit “run strata-poly on AMD cards through the HIP backend” (6 files · Python, C).
Answer from PolyStrata's real Python source instead of memory (AI, prompts and agents).

Example questions

Where does PolyStrata handle “run strata-poly on AMD cards through the HIP backend”?
How does PolyStrata implement anthropic-api?
What does include do in PolyStrata?

Paste it into your AI agent. It clones the repo at the pinned commit and indexes it on your machine.

Search the GitHub repository VecSzn/PolyStrata with XERJ (https://hub.xerj.org/corpus/vecszn--polystrata).
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/VecSzn/PolyStrata PolyStrata && git -C PolyStrata checkout 44b58c6ad11e7fef7c75e1d73353ee95210641d0
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./PolyStrata --url http://127.0.0.1:9200 --prefix polystrata --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: MIT. Keep the copyright notice and credit the authors.

corpus vecszn--polystrata · AI, prompts and agents
Related corpora: gorilla, dunorth595--ai-agent-chat, dynalm-project/dynalm, manuelgscom/dale
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 774

VecSzn/PolyStrata

Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost

On GitHub: 2,930 commits · 103 forks · created 2026-10 · last push 2026-10-29

Languages: C++ 62%, Python 22%, Cuda 13%

44b58c6ad1 poly: run strata-poly on AMD cards through the HIP backend

selected commit: 6 files · 170 lines · Python, C · the project root, include, src/poly

The corpus is the whole repository at the pinned commit, not only the files of the selected commit.

live on the hub · licence clearedcorpus vecszn--polystrataAIMITanthropic-apicudagemmaggufglminference-engine agreed 2026-10-16

[![XERJ Corpus Hub contributor](https://hub.xerj.org/contributors/iMilnb/badge.svg)](https://hub.xerj.org/contributors/iMilnb)

Included with the author's permission (email, 2026-10-16), under each repository's own licence, with attribution. Own more repositories? Sign in with GitHub and add them. Want something removed? Reply to the email, withdraw it on /add, or open an issue on xerj-org/xerj.