cortexdb
AI memory and a knowledge graph in one SQLite file. Pure Go: vectors, RAG, agent memory, RDF/SPARQL, Cypher, 80+ MCP tools. Works without an embedding model
What XERJ indexed
Snapshot
The whole repository at commit e0ee5fd3b3 (2026-10-18). main is 104 commits ahead.
Selected work
“a scope may list several values per field”. 7 files, 309 lines in pkg/authz, pkg/rpcserver.
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
embeddingsllmvector-databasevector-searchragsqlitehindsightagent-memory
Example questions
- How does cortexdb implement embeddings?
- Where does cortexdb handle “a scope may list several values per field”?
- What does pkg/authz do in cortexdb?
Inside the indexed corpus
- Languages by size: Go 95.1%, JavaScript 1.5%, Rust 1.3%, Python 1.2%, TypeScript 0.7%.
- On GitHub since 2025-08-07, last push 2026-10-29, 837 commits on main.
- The pin is 104 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for liliang-cn/cortexdb on 2026-10-29, and the LICENSE file at commit e0ee5fd3b3 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Lauro Foletti (@lfoletti) has 1 selected repository on the hub.
Using XERJ with cortexdb
- A local search tool for Codex and Cursor cortexdb is tagged claude-code on GitHub.
- Local code search MCP that uses fewer tokens than grep
- RAG without a vector database: one hybrid index cortexdb is tagged embeddings on GitHub.
- Search API or a vector database for agent memory?
The prompt
Paste it into your AI agent. It clones liliang-cn/cortexdb at the pinned commit and indexes it on your machine.
Search the GitHub repository liliang-cn/cortexdb with XERJ (https://hub.xerj.org/corpus/liliang-cn--cortexdb). 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/liliang-cn/cortexdb cortexdb && git -C cortexdb checkout e0ee5fd3b30d6a99c9b9c22aa35759f3fa95239c 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./cortexdb --url http://127.0.0.1:9200 --prefix cortexdb --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
Lauro FolettiAI, prompts and agents corporaxerj-blogpostsvectra-coremilvushsuanshao/AgentMemoryaistastudio/mycdevYRPauli/looma
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.