Tugrul Guner
Tugrul Guner'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 @tugrulguner 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 intpot corpus
tugrulguner/intpot: Define Python tools once and serve them as a Typer CLI, FastAPI app, or FastMCP server: or convert existing apps between all three
- Look up how intpot implements cli, code-generation, converter, with answers cited to file and line.
- Answer from intpot's real source instead of memory (AI, prompts and agents).
- How does intpot implement cli?
Search the GitHub repository tugrulguner/intpot with XERJ (https://hub.xerj.org/corpus/tugrulguner--intpot). 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/tugrulguner/intpot intpot && git -C intpot checkout f167cd4bac3931da063cc5bc43d7b2905054815e 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./intpot --url http://127.0.0.1:9200 --prefix intpot --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 tugrulguner--intpot · AI, prompts and agents
Related corpora: fastmcp, lexbuild, alok-108/phantom, IncidentFlow-io/incidentflow-mcp
AI search and retrieval with XERJ · Case study: reference coding for agents
Selected work
tugrulguner/intpot
Define Python tools once and serve them as a Typer CLI, FastAPI app, or FastMCP server: or convert existing apps between all three
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
tugrulguner/summonpot
A contract-first Python framework for modernizing APIs for AI through exact application behavior and explicitly bounded agent-owned decisions
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
tugrulguner/dexpot
A synchronous Python API framework with adaptive GIL and free-threaded execution
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
tugrulguner/lifepot
A bounded, replayable artificial-life laboratory where Jev proposes ecosystem rules and deterministic code runs every organism
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
tugrulguner/refpot
A custom embedded C++ database engine with a small Python API for durable CRUD and explicit transactions. Experimental alpha
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
tugrulguner/utilitypot
Open-source browser tools for data, text, diagrams and planning: eight browser-local workflows, including screenshot OCR, redaction and spreadsheet diff, plus three disclosed, bounded AI tools
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
tugrulguner/skillpot
Practical agent skills for building, researching, and presenting real work. Clear inputs, useful artifacts, explicit checks. In development
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/tugrulguner)
Included with the author's permission (email, 2026-10-15), 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.