llm-dev-kit
Local-first, self-hosted LLM workspace: Next.js chat, RAG over your PDFs, Ollama offline or cloud models via LiteLLM, MCP tools, and a plugin core. Runs entirely on your machine with Docker Compose
What XERJ indexed
Snapshot
The whole repository at commit 759dd05a8b (2026-10-24). main is 9 commits ahead.
Selected work
“add overview and API key management features”. 34 files, 2,316 lines in web.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-26. 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
chromadbdocker-composefastapilitellmllmlocal-firstmcpnextjs
Example questions
- How does llm-dev-kit implement chromadb?
- Where does llm-dev-kit handle “add overview and API key management features”?
- What does web do in llm-dev-kit?
Inside the indexed corpus
- 408 files, 1.8 MB in total, about 4.6 KB per file.
- The selected commit changed 34 of those files (8.3%).
- Languages by size: Python 52.8%, TypeScript 45.1%, CSS 1.1%, Dockerfile 0.6%, HTML 0.2%.
- On GitHub since 2025-09-13, last push 2026-10-28, 151 commits on main.
- The pin is 9 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for sameeralam3127/llm-dev-kit on 2026-10-31, and the LICENSE file at commit 759dd05a8b was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
SAMEER ALAM (@sameeralam3127) has 1 selected repository on the hub.
Using XERJ with llm-dev-kit
- Code search MCP for Claude Code: cite file:line, not grep llm-dev-kit is tagged mcp on GitHub.
- What is an MCP memory server?
- RAG without a vector database: one hybrid index llm-dev-kit is tagged rag on GitHub.
- Search API or a vector database for agent memory?
The prompt
Paste it into your AI agent. It clones sameeralam3127/llm-dev-kit at the pinned commit and indexes it on your machine.
Search the GitHub repository sameeralam3127/llm-dev-kit with XERJ (https://hub.xerj.org/corpus/sameeralam3127--llm-dev-kit). 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/sameeralam3127/llm-dev-kit llm-dev-kit && git -C llm-dev-kit checkout 759dd05a8bbbbb10924ecf17186186b06ab5aa53 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./llm-dev-kit --url http://127.0.0.1:9200 --prefix llm-dev-kit --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
SAMEER ALAMAI, prompts and agents corporadunorth595--ai-agent-chatdunorth595--ai-agent-memoryfastragantiv/matemanu69x/transaliyevaladddin/AladdinAI
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.