Oleksii Pylypchuk

Corpus Hub contributor since 2026-10-24

Oleksii Pylypchuk'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

5files

743lines

★ 1GitHub stars on repo

Totals across every corpus @alpiua 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 contextunity-forge-mcp corpus

ContextUnity/contextunity-forge-mcp: Local code graph, documentation, and task coordination server for AI coding agents. It indexes supported source files and Markdown into a…

Look up how contextunity-forge-mcp implements code-graph, contract-driven-development, contract-lifecycle-management, with answers cited to file and line.
Reuse a worked example: the commit “archive verified delivery and declarative parser fram…” (5 files · Rust).
Answer from contextunity-forge-mcp's real Rust source instead of memory (AI, prompts and agents).

Example questions

How does contextunity-forge-mcp implement code-graph?
What does src/engine do in contextunity-forge-mcp?

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

Search the GitHub repository ContextUnity/contextunity-forge-mcp with XERJ (https://hub.xerj.org/corpus/contextunity--contextunity-forge-mcp).
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/ContextUnity/contextunity-forge-mcp contextunity-forge-mcp && git -C contextunity-forge-mcp checkout 1924fa0cd934fa1413aa30bfcf7e22833ee0ebc1
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./contextunity-forge-mcp --url http://127.0.0.1:9200 --prefix contextunity-forge-mcp --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 contextunity--contextunity-forge-mcp · AI, prompts and agents
Related corpora: flexrag, r2r-mcp, anything-llm, agno
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 1

ContextUnity/contextunity-forge-mcp

1924fa0cd9 milestone(021): archive verified delivery and declarative parser fram…

selected commit: 5 files · 743 lines · Rust · src/engine

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

selected · in licence reviewcorpus contextunity--contextunity-forge-mcpAIMITcode-graphcontract-driven-developmentcontract-lifecycle-management agreed 2026-10-24

Not installable yet: this corpus is not in the hub registry until its licence review passes, so xerj corpus add and xerj ask cannot fetch it. It becomes installable when this card says live in the hub.

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

Included with the author's permission (email, 2026-10-24), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.