HyperMnesia

Self-hosted long-term memory for AI coding agents: Postgres+pgvector doc-RAG (component/constraint map + hybrid RRF + cross-encoder rerank) and bi-temporal personal memory. MCP-native, local-model friendly

A new way for AI to search for data
View on GitHub
16GitHub stars
160commits on main
2forks

Python 56.7%, Rust 34.9%, PLpgSQL 6.4%, Shell 1.9% · created 2026-08-30 · last push 2026-10-31

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 29f0b53de4 (2026-10-05).

Selected work

Ruslan Semov
@Recluse

“expose scoped project counts and hash freshness”. 3 files, 258 lines in ci, tests, mcp-server.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-13. 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-agentsclaude-codeembeddingsllmmcpmemorypgvectorpostgres

Example questions

Inside the indexed corpus

Licence on GitHub and in the corpus

GitHub reported MIT for Recluse/HyperMnesia on 2026-10-31, and the LICENSE file at commit 29f0b53de4 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.

Contributors

Ruslan Semov (@Recluse) has 1 selected repository on the hub.

Using XERJ with HyperMnesia

The prompt

Paste it into your AI agent. It clones Recluse/HyperMnesia at the pinned commit and indexes it on your machine.

Search the GitHub repository Recluse/HyperMnesia with XERJ (https://hub.xerj.org/corpus/recluse--hypermnesia).
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/Recluse/HyperMnesia HyperMnesia && git -C HyperMnesia checkout 29f0b53de4b49e05379e1294ea7f0c16553de45d
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./HyperMnesia --url http://127.0.0.1:9200 --prefix hypermnesia --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

Stats: GitHub API, fetched 2026-10-31. Selected work and consent: the XERJ registry.