collattice
Collattice: a lightweight, self-hosted kanban board built for human-agent collaboration. Single executable, embedded SQLite, real-time SSE, and a built-in MCP server so AI agents work the board alongside you
What XERJ indexed
Snapshot
The whole repository at commit 2287b54f26 (2026-10-24). main is 7 commits ahead.
Selected work

“stop logging the admin auth key on every start; add --reset-admi…”. 10 files, 670 lines in backend.
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
ai-agentsdotnetkanbankanban-boardmcpmodel-context-protocolproject-managementreact
Example questions
- How does collattice implement ai-agents?
- What does backend do in collattice?
- Show the dotnet code in collattice.
Inside the indexed corpus
- 510 files, 5.8 MB in total, about 11.7 KB per file.
- The selected commit changed 10 of those files (2.0%).
- Languages by size: C# 68.3%, TypeScript 27.9%, Shell 2.9%, CSS 0.5%, PowerShell 0.4%.
- On GitHub since 2026-03-13, last push 2026-10-27, 358 commits on main.
- The pin is 7 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for MrBildo/collattice on 2026-10-31, and the LICENSE file at commit 2287b54f26 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Bill Wheelock (@MrBildo) has 1 selected repository on the hub.
Using XERJ with collattice
- Code search MCP for Claude Code: cite file:line, not grep collattice is tagged mcp on GitHub.
- What is an MCP memory server?
- Full-text search a SQLite database (FTS5 alternative) collattice is tagged sqlite 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 MrBildo/collattice at the pinned commit and indexes it on your machine.
Search the GitHub repository MrBildo/collattice with XERJ (https://hub.xerj.org/corpus/mrbildo--collattice). 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/MrBildo/collattice collattice && git -C collattice checkout 2287b54f26b680165d297ef4e79ff552530b2b94 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./collattice --url http://127.0.0.1:9200 --prefix collattice --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
Bill WheelockAI, prompts and agents corporabebopdunorth595--ai-agent-memoryharperMojolaoluwaOlanusi/Tudufazal305/traxakremenetsky/kanban-starlane
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.