cogito-estella
Latent Graph Engine: non-autoregressive concept-to-knowledge-graph decoding in the SONAR space
What XERJ indexed
Snapshot
The whole repository at commit 4852b18789 (2026-10-14). main is 53 commits ahead.
Selected work

“deep=True loads the graph model once inside a lite session and …”. 4 files, 198 lines in src/cogito_estella, tests.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-15. 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-memoryembeddingsgraphragknowledge-graphlangchainllamaindexmultilingualneo4j
Example questions
- How does cogito-estella implement agent-memory?
- What does src/cogito_estella do in cogito-estella?
- Show the embeddings code in cogito-estella.
Inside the indexed corpus
- 96 files, 2.0 MB in total, about 21.2 KB per file.
- The selected commit changed 4 of those files (4.2%).
- Languages by size: Python 99.8%, JavaScript 0.2%.
- On GitHub since 2026-08-26, last push 2026-10-15, 232 commits on main.
- The pin is 53 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported Apache-2.0 for DeliVali/cogito-estella on 2026-10-31, and the LICENSE file at commit 4852b18789 was reviewed as Apache-2.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Jeffrey Romero Del Val (@DeliVali) has 1 selected repository on the hub.
Using XERJ with cogito-estella
- RAG without a vector database: one hybrid index cogito-estella is tagged embeddings on GitHub.
- Search API or a vector database for agent memory?
- What is agentic memory? A plain answer cogito-estella is tagged agent-memory on GitHub.
- XERJ vs Mem0, Zep, Letta and Cognee for agent memory
The prompt
Paste it into your AI agent. It clones DeliVali/cogito-estella at the pinned commit and indexes it on your machine.
Search the GitHub repository DeliVali/cogito-estella with XERJ (https://hub.xerj.org/corpus/delivali--cogito-estella). 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/DeliVali/cogito-estella cogito-estella && git -C cogito-estella checkout 4852b18789681004c5bd33f091475beb926920d2 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./cogito-estella --url http://127.0.0.1:9200 --prefix cogito-estella --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: Apache-2.0. Keep the copyright notice and credit the authors.
Related
Jeffrey Romero Del ValAI, prompts and agents corporafastraggraphragdunorth595--ai-agent-memorytejas-parjane/business-intelligent-rag-agentschwabauerbriantomas-gif/m2m-vector-searchmuzakkirhussain011/wardowl
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.