Credit
The Independent 100 list was curated by dan (@irl_danB) and published on 2026-09-24 at independent.prose.md (announcement). The ranks and section names are his, and number 100 is his open wild-card slot. This study is ours and is not endorsed by him or by anyone on the list.
What they publicly do
Pseudonymous account. The GitHub account Tenobrus publishes small agent tools, including a Claude Code skill that implements Recursive Language Models [Verified: github.com/Tenobrus/claude-rlm].
- X profile: x.com/tenobrus
- GitHub: github.com/Tenobrus
Public work
- claude-rlm repo no license file last activity 2026-02-09 · 95 GitHub stars on 2026-09-24
A Claude Code skill implementing Recursive Language Models (Zhang, Kraska, Khattab 2026). The long input is kept as an external variable; the model inspects it with code and recursively calls sub-agents on slices, as an alternative to lossy compaction.
- graphglyph repo no license file last activity 2026-05-23 · 76 GitHub stars on 2026-09-24
Encodes text as reversible unit-distance graph images.
- no-sigmoids repo no license file last activity 2026-02-06 · 3 GitHub stars on 2026-09-24
An addendum using new METR time-horizon data to challenge a 'plateau' hypothesis in a 2026 paper.
Licenses of GitHub repositories are from the authenticated GitHub license API on 2026-09-25, one row per repository in evidence/licenses.jsonl (“no license file” means the API found none; “license file present, not recognised by GitHub” means GitHub could not classify it). Other licenses are as the source states. Check the license file before reusing anything.
Relevance to our work
4 of 5 lenses: agents, memory, orchestration, security
claude-rlm addresses long-context handling in Claude Code skills, as an alternative to lossy compaction. It has no license file, so the skill is study-only.
Scored 0 to 5 against the study’s relevance rubric: 5 means public, openly licensed work squarely in our lanes that we could study or adopt now, and 1 means little connection to our work. The score is one reviewer’s judgement of how much this public work bears on our own work. It is not a ranking of people and says nothing about the person or the quality of their work.
What we would study next
- Read claude-rlm and benchmark RLM-style recursive slicing against compaction plus ee/cass recall on a long-log analysis task (github.com/Tenobrus/claude-rlm). It may beat summarization for huge inputs such as session logs and corpora. Effort: medium.
Before reusing anything: No LICENSE file on any listed repo (all rights reserved by default): study, don't vendor.
Sources
Overall confidence in this record: High. Sources were read on 2026-09-24 and every link was checked on 2026-09-25. The full record is line 51 of people.jsonl.
Limits
Not verified: How well claude-rlm performs (no benchmarks were read).
This record comes from a first-pass survey of public material by an AI agent session on 2026-09-24, edited for publication on 2026-09-25. Nothing was installed or run for it. Roles, stars and licenses change; see the study’s limits.
Request a correction
Is something about this record wrong or out of date, or would you rather not be covered? Open a correction (a GitHub issue form with this page’s address filled in). A request to remove a record is honoured without argument; accepted corrections are recorded in the changelog with the date.