mind
Persistent local memory for AI coding agents. Preserve decisions and project context across sessions, compaction, and tools
What XERJ indexed
Snapshot
The whole repository at commit b1e41202f4 (2026-10-26). main is 10 commits ahead.
Selected work

“OmniMemEval RAG A/B and GPT-6 Luna low evaluation”. 8 files, 159 lines in benchmarks.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-27. 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-memoryai-agentsantigravityclaude-codecodexcursordeveloper-toolsgemini-cli
Example questions
- How does mind implement agent-memory?
- Where does mind handle “OmniMemEval RAG A/B and GPT-6 Luna low evaluation”?
- What does benchmarks do in mind?
Inside the indexed corpus
- Languages by size: TypeScript 81%, JavaScript 8.8%, Gherkin 5.6%, CSS 2.3%, Shell 1.4%.
- On GitHub since 2025-04-27, last push 2026-10-27, 140 commits on main.
- The pin is 10 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for GabrielMartinMoran/mind on 2026-10-29, and the LICENSE file at commit b1e41202f4 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Gabriel Martín Moran (@GabrielMartinMoran) has 1 selected repository on the hub.
Using XERJ with mind
- Code search MCP for Claude Code: cite file:line, not grep mind is tagged mcp on GitHub.
- What is an MCP memory server?
- A local search tool for Codex and Cursor mind 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 GabrielMartinMoran/mind at the pinned commit and indexes it on your machine.
Search the GitHub repository GabrielMartinMoran/mind with XERJ (https://hub.xerj.org/corpus/gabrielmartinmoran--mind). 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/GabrielMartinMoran/mind mind && git -C mind checkout b1e41202f42fd3195dabaa2c726523c2eb22e800 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./mind --url http://127.0.0.1:9200 --prefix mind --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
Gabriel Martín MoranAI, prompts and agents corporaxerj-blogpostsfaahagnojayzeng/agentmemorykanghyunsoon/duojustn-hyeok/brgr
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.