summonpot
A contract-first Python framework for modernizing APIs for AI through exact application behavior and explicitly bounded agent-owned decisions
What XERJ indexed
Snapshot
The whole repository at commit c7fa71a93c (2026-10-15). main is 29 commits ahead.
Selected work
“constrain agent choices to validated producer candidates”. 12 files, 1,093 lines in tests, src/summonpot, examples.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-15. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
ai-nativeapideveloper-toolspythonagentic-aiapi-frameworkhttp-apiopenapi
Example questions
- How does summonpot implement ai-native?
- Where does summonpot handle “constrain agent choices to validated producer candidates”?
- What does src/summonpot do in summonpot?
Inside the indexed corpus
- Languages by size: Python 82.9%, JavaScript 7.4%, MDX 6.3%, Astro 2.6%, CSS 0.7%.
- On GitHub since 2026-08-10, last push 2026-10-31, 492 commits on main.
- The pin is 29 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for tugrulguner/summonpot on 2026-10-31, and the LICENSE file at commit c7fa71a93c was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Tugrul Guner (@tugrulguner) has 7 selected repositories on the hub.
Their other repository pages: tugrulguner/intpot, tugrulguner/dexpot, tugrulguner/lifepot, tugrulguner/refpot, tugrulguner/utilitypot, tugrulguner/skillpot.
Using XERJ with summonpot
- Search an OpenAPI spec so an agent can find endpoints summonpot is tagged openapi on GitHub.
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Ask questions about a GitHub repo without cloning it
- Index a reference library for a coding agent
The prompt
Paste it into your AI agent. It clones tugrulguner/summonpot at the pinned commit and indexes it on your machine.
Search the GitHub repository tugrulguner/summonpot with XERJ (https://hub.xerj.org/corpus/tugrulguner--summonpot). 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/summonpot summonpot && git -C summonpot checkout c7fa71a93c61d76a4dfa70f44bea723eb10e26d1 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./summonpot --url http://127.0.0.1:9200 --prefix summonpot --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.
Related
Tugrul GunerAI, prompts and agents corporainstructoropenapi-specbox-openapidymmond/ravynhuynguyengl99/agent-graph-engineeringr28ai/charter
Stats: GitHub API, fetched 2026-10-31. Selected work and consent: the XERJ registry.