Thomas Konstantinovsky
Thomas Konstantinovsky's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.
Totals across every corpus @MuteJester appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.
What an agent can do with the GenAIRR corpus
MuteJester/GenAIRR: Fast simulator of BCR and TCR sequences with full ground-truth annotations: V(D)J recombination, somatic hypermutation and sequencing…
- Look up how GenAIRR implements airr-seq, bcr, benchmarking, with answers cited to file and line.
- Reuse a worked example: the commit “preserve duplex truth through clonal families” (32 files · Python, Rust).
- Answer from GenAIRR's real Python source instead of memory (Health and clinical reference).
- Where does GenAIRR handle “preserve duplex truth through clonal families”?
- How does GenAIRR implement airr-seq?
- What does audit-docs do in GenAIRR?
Search the GitHub repository MuteJester/GenAIRR with XERJ (https://hub.xerj.org/corpus/mutejester--genairr). 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/MuteJester/GenAIRR GenAIRR && git -C GenAIRR checkout 18ecdf6e9bb180712e0f61f12cdbe55706775ee5 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./GenAIRR --url http://127.0.0.1:9200 --prefix genairr --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: GPL-3.0. Read it for the approach only, do not copy code.
corpus mutejester--genairr · Health and clinical reference
Related corpora: synthea, scispacy, davewalker5/MolecularClockSimulation, scikit-bio/scikit-bio
Case study: reference coding for agents
Selected work
MuteJester/GenAIRR
Fast simulator of BCR and TCR sequences with full ground-truth annotations: V(D)J recombination, somatic hypermutation and sequencing artifacts across 23 species. Rust core with a Python API, for training and benchmarking AIRR-seq tools
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
Sign in with GitHub or Hugging Face to see more: every selected commit in full (commit date, every folder, licence review state, pin) and the pack builds of each corpus.
[](https://hub.xerj.org/contributors/MuteJester)
Included with the author's permission (email, 2026-10-24), under each repository's own licence, with attribution. Own more repositories? Sign in with GitHub and add them. Want something removed? Reply to the email, withdraw it on /add, or open an issue on xerj-org/xerj.