webgpt-as-codex
Turn ChatGPT into a local coding/computer agent. No extra API tokens or API fees; use your existing ChatGPT plan for more local compute…
A new way for AI to search for data
3GitHub stars
What XERJ indexed
Selected work
“enforce machine-level exactly-once handoff”. 7 files, 1,001 lines in src/webgpt_as_codex, tests.
Licence
The repository
Apache-2.0
Checked by a person at the pinned commit.
The XERJ corpus
Apache-2.0, with credit
The author agreed by email on 2026-10-22. Same terms as the repository. Answers name the repo, the commit and the file:line.
in licence reviewnot in the hub yetsuggested use: adapt with attribution
Example questions
- Where does webgpt-as-codex handle “enforce machine-level exactly-once handoff”?
- What does src/webgpt_as_codex do in webgpt-as-codex?
The prompt
Paste it into your AI agent. It clones lite-milkfrog/webgpt-as-codex at the pinned commit and indexes it on your machine.
Search the GitHub repository lite-milkfrog/webgpt-as-codex with XERJ (https://hub.xerj.org/corpus/lite-milkfrog--webgpt-as-codex). 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/lite-milkfrog/webgpt-as-codex webgpt-as-codex && git -C webgpt-as-codex checkout d711110d9648bda9692233bfd70beffa1214e66b 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./webgpt-as-codex --url http://127.0.0.1:9200 --prefix webgpt-as-codex --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: Apache-2.0. Keep the copyright notice and credit the authors.
Related
milkfrogAI, prompts and agents corpora
Selected work and consent: the XERJ registry.