Small-model reasoning and adaptation research
  • Python 80%
  • HTML 19.6%
  • Shell 0.2%
  • CSS 0.1%
  • Astro 0.1%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
elsie b9273e2a16
All checks were successful
checks / select relevant integrity checks (push) Successful in 11s
checks / E01 candidate surface sufficiency (push) Has been skipped
checks / DMS-003 protocol freeze integrity (push) Has been skipped
checks / DMS-003 CPU successor integrity (push) Has been skipped
checks / resource accounting and workflow consistency (push) Has been skipped
checks / documentation integrity (push) Successful in 10s
Merge pull request 'research: preserve reviewed three-direction checkpoint' (#191) from research/session-checkpoint-20261025 into main
2026-10-25 19:03:22 +00:00
.github Remove obsolete operating roles and procedural approval gates 2026-10-16 14:06:24 -04:00
agents Replace obsolete lab governance with bounded research workflow 2026-10-06 22:21:34 -04:00
configs Remove remaining named-role instruction routing 2026-10-16 14:14:57 -04:00
continuum_research Preserve bounded F0 F1 B0 and F3 instruments with qualified results 2026-10-17 09:51:56 -04:00
docs research: report audited PDX1 null retention and planning depth results 2026-10-24 07:03:19 -04:00
experiments Preserve qualified C1 and DMS research from historical PRs 2026-10-18 00:04:34 -04:00
reports research: report audited PDX1 null retention and planning depth results 2026-10-24 07:03:19 -04:00
research research: preserve reviewed three-direction checkpoint 2026-10-25 19:02:25 +00:00
results research: report audited PDX1 null retention and planning depth results 2026-10-24 07:03:19 -04:00
scripts research: freeze reviewed bounded prospective symbolic qualification 2026-10-19 20:03:57 -04:00
site docs(site): reconcile E01 provenance and link progress report 2026-09-21 02:05:14 -04:00
src/smolmodelcompany Integrate current main and regenerate retained X11 closeout ledger 2026-10-17 23:55:02 -04:00
templates Remove obsolete operating roles and procedural approval gates 2026-10-16 14:06:24 -04:00
tests research: freeze reviewed bounded prospective symbolic qualification 2026-10-19 20:03:57 -04:00
.gitattributes research: report audited PDX1 null retention and planning depth results 2026-10-24 07:03:19 -04:00
.gitignore research: freeze MEX1 structure split models and pre-final reference gates 2026-10-23 22:53:12 -04:00
AGENTS.md Remove remaining named-role instruction routing 2026-10-16 14:14:57 -04:00
LICENSE Initial commit 2026-09-20 15:09:11 -04:00
pyproject.toml feat: establish SMC-001 RD1 apparatus (#37) 2026-09-21 16:34:39 -04:00
README.md Preserve Continuum research in canonical SMC 2026-10-16 09:38:15 -04:00
WEEKEND_RESEARCH_BRIEF.md Merge pull request #73: census ruling 01 — decision identity, R8 statistic, standing-rule boundary 2026-09-26 11:53:59 +00:00

The Smol Model Company

Research small models that reason, compose skills and adapt, with reproducible evidence and practical resource limits. Transfer mechanisms that work into a useful local assistant.

Public site: thesmolmodel.co. Canonical work: Forgejo.

Working here

Read AGENTS.md and the short research contract. Cassie approves a research question and bounded resources once; agents execute, keep evidence and report. Agents own JSON/configs/receipts. Ordinary code/docs use relevant tests, a PR and plain-language approval rather than research-admission paperwork. See workflow and compute.

Research and evidence

The experience-consolidation program records a research direction; task-specific current instructions determine the next experiment. The evaluation principles guide fair comparisons, held-out evaluation and honest claims. Results are generated from retained run reports.

Continuum preserves the frozen synthetic adaptation study, including its negative results, source/config identities, reproduction checks and separate private-evidence handoff. See its migration record for provenance and follow-up.

Earlier research designs, backlog assignments, decisions and experiment protocols remain evidence of their time, not additional active governance. Preserve them and their corrections. GitHub is a suspended mirror, not a second work queue.

Keep exact code/config/data/model identities and reproduction commands with measurements, failures, costs and limitations. Keep large weights/datasets and private information outside Git. The MIT license does not relicense third-party artifacts. No new empirical execution or spending is authorized by this reset.