garda-agent-orchestrator
Governed local runtime for AI coding agents: task lifecycle, mandatory gates, reviews, doc-impact checks, and auditable completion
What XERJ indexed
Snapshot
The whole repository at commit 3aae7e2715 (2026-10-23). master is 4 commits ahead.
Selected work
“stack-neutral file-name review triggers for 1.4.4”. 12 files, 335 lines in src/gates, template, tests.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-24. 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
agent-orchestrationai-agentsai-codingaudit-trailcode-reviewcoding-agentsquality-gatesagent-control
Example questions
- How does garda-agent-orchestrator implement agent-orchestration?
- Where does garda-agent-orchestrator handle “stack-neutral file-name review triggers for 1.4.4”?
- What does src/gates do in garda-agent-orchestrator?
Inside the indexed corpus
- 2,535 files, 47.1 MB in total, about 19.0 KB per file.
- The selected commit changed 12 of those files (0.5%).
- Languages by size: TypeScript 99%, JavaScript 1%, Shell 0%.
- On GitHub since 2026-04-13, last push 2026-10-28, 2,219 commits on master.
- The pin is 4 commits behind master; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported Apache-2.0 for Garda-Studio/garda-agent-orchestrator on 2026-10-31, and the LICENSE file at commit 3aae7e2715 was reviewed as Apache-2.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Dmytro Shubchynskyi (@Shubchynskyi) has 1 selected repository on the hub.
Using XERJ with garda-agent-orchestrator
- A local search tool for Codex and Cursor garda-agent-orchestrator is tagged ai-coding on GitHub.
- Local code search MCP that uses fewer tokens than grep
- Index a monorepo so your agent stops reading the whole repo The pinned tree has 2,535 files.
- 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 Garda-Studio/garda-agent-orchestrator at the pinned commit and indexes it on your machine.
Search the GitHub repository Garda-Studio/garda-agent-orchestrator with XERJ (https://hub.xerj.org/corpus/garda-studio--garda-agent-orchestrator). 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/Garda-Studio/garda-agent-orchestrator garda-agent-orchestrator && git -C garda-agent-orchestrator checkout 3aae7e2715fc411320ea63bc3be46ac115d19ada 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./garda-agent-orchestrator --url http://127.0.0.1:9200 --prefix garda-agent-orchestrator --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
Dmytro ShubchynskyiAI, prompts and agents corporaxobotyi--cc-foundry-the-coderxobotyi--cc-foundry-cliatoma-run--atomadylan-murray/agent-deskdagoSte/squadratlbx-ai/tlbx
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.