Emanuele Cella
Emanuele Cella'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.
Totals across every corpus @EmanueleCell4 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 elliot-mcp corpus
EmanueleCell4/elliot-mcp: Your agent says it's done. Elliot checks. Independent verification for code written by AI agents
- Look up how elliot-mcp implements ai-agents, claude-code, code-review, with answers cited to file and line.
- Reuse a worked example: the commit “replace previous Elliot with validated outcome verification and…” (16 files · JavaScript).
- Answer from elliot-mcp's real JavaScript source instead of memory (AI, prompts and agents).
- How does elliot-mcp implement ai-agents?
- What does test do in elliot-mcp?
Search the GitHub repository EmanueleCell4/elliot-mcp with XERJ (https://hub.xerj.org/corpus/emanuelecell4--elliot-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/EmanueleCell4/elliot-mcp elliot-mcp && git -C elliot-mcp checkout 912c400ca3e0cb4b0671bfb6c1e574dd5a125259 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./elliot-mcp --url http://127.0.0.1:9200 --prefix elliot-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 emanuelecell4--elliot-mcp · AI, prompts and agents
Related corpora: owasp-cheatsheets, nuclei-templates, chadixearth/graphyloop, GabrielMartinMoran/mind
AI search and retrieval with XERJ · Case study: reference coding for agents
Selected work
EmanueleCell4/elliot-mcp
Your agent says it's done. Elliot checks. Independent verification for code written by AI agents
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
Sign in with GitHub or Hugging Face to see more: every selected commit in full (commit date, every folder, licence review state, pin) and the pack builds of each corpus.
[](https://hub.xerj.org/contributors/EmanueleCell4)
Included with the author's permission (email, 2026-10-25), 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.