commitlore
Git-native decision memory for Claude Code, Codex, Cursor and other coding agents. Preserve constraints and rejected alternatives; surface only the decisions still in force
What XERJ indexed
Snapshot
The whole repository at commit 2dbe305011 (2026-10-18). main is 28 commits ahead.
Selected work
“withdraw a staged capture, and call a replaced one repl…”. 5 files, 402 lines in test, src/core, src/commands.
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
claude-codegitmcpagent-memoryai-memorycodexcoding-agentscontext-engineering
Example questions
- How does commitlore implement claude-code?
- What does src/core do in commitlore?
- Show the git code in commitlore.
Inside the indexed corpus
- Languages by size: TypeScript 94.2%, JavaScript 4.2%, Shell 0.9%, PowerShell 0.7%, Tape 0%.
- On GitHub since 2026-07-26, last push 2026-10-18, 1,888 commits on main.
- The pin is 28 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for MongLong0214/commitlore on 2026-10-29, and the LICENSE file at commit 2dbe305011 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
MongLong0214 (@MongLong0214) has 1 selected repository on the hub.
Using XERJ with commitlore
- Code search MCP for Claude Code: cite file:line, not grep commitlore is tagged mcp on GitHub.
- What is an MCP memory server?
- A local search tool for Codex and Cursor commitlore is tagged claude-code on GitHub.
- Local code search MCP that uses fewer tokens than grep
The prompt
Paste it into your AI agent. It clones MongLong0214/commitlore at the pinned commit and indexes it on your machine.
Search the GitHub repository MongLong0214/commitlore with XERJ (https://hub.xerj.org/corpus/monglong0214--commitlore). 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/MongLong0214/commitlore commitlore && git -C commitlore checkout 2dbe3050117e6e48a6ac795fc9c8b7c6fafbeb83 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./commitlore --url http://127.0.0.1:9200 --prefix commitlore --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
MongLong0214AI, prompts and agents corporaxerj-blogpostsdunorth595--ai-agent-memoryfaahAndreyBegma/NautelleAlekla0126/alchemist-coderordewell/ordewell
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.