Vestibule
Vestibule - A kernel-isolated code-execution sandbox for AI agents, as an MCP server. Run untrusted/questionable agent code safely: local, free, no cloud
What XERJ indexed
Snapshot
The whole repository at commit 9197a55d4c (2026-10-25). main is 16 commits ahead.
Selected work
“M2 step 2 second partial commit”. 10 files, 1,571 lines in tests, src/vestibule, the project root.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-25. 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-agentscode-executionisolationllmllm-toolsmcpmodel-context-protocolsandbox
Example questions
- How does Vestibule implement ai-agents?
- Where does Vestibule handle “M2 step 2 second partial commit”?
- What does src/vestibule do in Vestibule?
Inside the indexed corpus
- 70 files, 1.0 MB in total, about 14.9 KB per file.
- The selected commit changed 10 of those files (14.3%).
- Languages by size: Python 98.9%, Shell 1.1%.
- On GitHub since 2026-07-03, last push 2026-10-28, 69 commits on main.
- The pin is 16 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for victorperson999/Vestibule on 2026-10-31, and the LICENSE file at commit 9197a55d4c was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Victor (@victorperson999) has 1 selected repository on the hub.
Using XERJ with Vestibule
- Code search MCP for Claude Code: cite file:line, not grep Vestibule is tagged mcp on GitHub.
- What is an MCP memory server?
- Batch lookup CVE and GHSA IDs offline in one query Vestibule is tagged security on GitHub.
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
The prompt
Paste it into your AI agent. It clones victorperson999/Vestibule at the pinned commit and indexes it on your machine.
Search the GitHub repository victorperson999/Vestibule with XERJ (https://hub.xerj.org/corpus/victorperson999--vestibule). 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/victorperson999/Vestibule Vestibule && git -C Vestibule checkout 9197a55d4c6713e8d5bf70a5661c515002f8252e 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./Vestibule --url http://127.0.0.1:9200 --prefix vestibule --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
Victor AI, prompts and agents corporavuln-fix-commitsgarakmitre-cweNeevCloudAI/neev-sdk-jsErio-Harrison/nanosandboxcapsulerun/vpod
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.