Hirara
Self-hosted toolkit of tools for AI agents & LLMs: web search, PDF, OCR, Office, sandboxed code execution. Python SDK + MCP, no API keys
What XERJ indexed
Snapshot
The whole repository at commit 0a50290a32 (2026-10-23). main is 3 commits ahead.
Selected work
“Wire the agent essentials into the hub, SDK, compose and docs”. 9 files, 402 lines in hirara, the project root, hirara-hub.
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
agent-toolkitagent-toolsai-agentcode-executiondocument-extractionfastapillmmcp
Example questions
- How does Hirara implement agent-toolkit?
- Where does Hirara handle “Wire the agent essentials into the hub, SDK, compose and docs”?
- What does hirara do in Hirara?
Inside the indexed corpus
- 454 files, 3.5 MB in total, about 7.8 KB per file.
- The selected commit changed 9 of those files (2.0%).
- Languages by size: Python 93.4%, Rust 4.3%, Dockerfile 1.4%, Shell 0.8%.
- On GitHub since 2026-08-02, last push 2026-10-30, 79 commits on main.
- The pin is 3 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported Apache-2.0 for lucasdmarshall/Hirara on 2026-10-31, and the LICENSE file at commit 0a50290a32 was reviewed as Apache-2.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Kaung Myat San (@lucasdmarshall) has 1 selected repository on the hub.
Using XERJ with Hirara
- Code search MCP for Claude Code: cite file:line, not grep Hirara is tagged mcp on GitHub.
- What is an MCP memory server?
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Best grep alternative for AI coding agents (2026)
The prompt
Paste it into your AI agent. It clones lucasdmarshall/Hirara at the pinned commit and indexes it on your machine.
Search the GitHub repository lucasdmarshall/Hirara with XERJ (https://hub.xerj.org/corpus/lucasdmarshall--hirara). 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/lucasdmarshall/Hirara Hirara && git -C Hirara checkout 0a50290a328e5597954ecafaade79ca78c9fb96b 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./Hirara --url http://127.0.0.1:9200 --prefix hirara --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
Kaung Myat SanAI, prompts and agents corporaoxidize-pdfdunorth595--ai-agent-memorytexioEthos6/free-ocr-apiattnstack/docforgeopensandbox-group/OpenSandbox
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.