Item detail
github.com

karpathy/autoresearch

karpathy/autoresearch is a code repository that RepoRadar is tracking in its AI tooling section, currently rated Gold tier with a 'try now' verdict. It is written primarily in Python. Its strongest signal is workflow potential, scored 9.6 out of 10.

Score8.5
Popularity100.0
Risklow
TierGold
Score breakdown
Usefulness8.2
Novelty9.0
Momentum9.5
Maturity9.1
Open-source/build8.4
Evidence7.2
Workflow potential9.6
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Autoresearch belongs on RepoRadar because it ships a real, runnable autonomous-research primitive rather than a chat wrapper or skill collection. The agent edits the actual training code (`train.py`) -- architecture, optimizer, hyperparameters, batch size, everything -- not a config file or a `program.md` wrapper. The 5-minute wall-clock budget per experiment makes the loop tractable on a single

Who should use it

Single-GPU LLM pretraining research on an H100 with a 5-minute-per-experiment budget Autonomous overnight research loops where the agent edits the training code (architecture, optimizer, hyperparameters) and the human programs the program.md research-org specification Comparing architectural changes (e.g. attention variants, normalization, optimizer swaps) under a vocab-size-independent metric (val_bpb) Researchers who want a single-machine autonomous-research primitive instead of a cluster-only workflow Anyone who wants to study Muon + AdamW optimizer combinations on a small GPT model end-to-end Adopters who want MIT-licensed autonomous-research code with active macOS / Windows / MLX / AMD community forks

Who should skip it

Skip karpathy/autoresearch unless the captured evidence suggests it solves a problem you are actively working on.

About this signal

karpathy/autoresearch is tracked by RepoRadar as a code repository in the AI tooling section. First seen 2026-07-12; the source record was last checked on 2026-07-12. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, karpathy/autoresearch is strongest on workflow potential (9.6) and momentum (9.5) and weakest on setup ease (6.4) — a profile worth weighing against your own priorities. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The karpathy/autoresearch record combines a 8.5/10 composite score with separate popularity (100.0), risk (low), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to read AI benchmarks without getting fooled for the checklist behind this score.

Risk explanation

Last commit was 2026-03-26 (~3.5 months ago) -- under the cycle 141 4-month stale threshold but approaching it; the cycle-script chose the pick on the strength of the README's authoritative MIT declaration and Karpathy's MIT-by-convention track record (nanochat, llm.c, minbpe are all MIT); No LICENSE file at the repo root (raw main/LICENSE returns 404); the MIT declaration lives only in the README's `## License / MIT` section -- authoritative for the maintainer's intent but weaker than a dedicated LICENSE file for downstream legal review; Single-machine scope: the README targets a single H100 (or comparable) GPU; multi-GPU / cluster workflows require the maintainer's separate `nanochat` project (56,175★) or the active community forks; Default-branch master is unusual for a Python project in 2026 (most Python projects default to main); not a risk per se but worth noting for tooling that branches off.

Evidence links
Closest alternatives / related signals
autonomous-research ai-agent single-gpu llm-training pretraining nanochat karpathy muon-optimizer
Verification record

What RepoRadar actually verified

Discovered

Automated discovery and source capture. Last checked 2026-08-13T20:20:15Z.

No editorial or hands-on review is claimed. This record remains at Discovered.

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

25 dated snapshots retained from 2026-07-12 through 2026-08-13; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.5 current · +0.0 net
Repository momentum3.6 current · -5.9 net
GitHub stars (observed)93,805 current · +2,885 net
GitHub stars93,805 exact observation
VersionNot reported by source
Last releaseNot reported by source
Maintenanceslowing
Current risklow
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-138.53.693,805lowtry nowslowing
2026-08-128.53.693,731lowtry nowslowing
2026-08-118.53.693,644lowtry nowslowing
2026-08-108.53.693,552lowtry nowslowing
2026-08-098.53.693,480lowtry nowslowing
2026-08-088.54.093,420lowtry nowslowing
2026-08-078.53.692,863lowtry nowslowing
2026-08-068.59.593,296lowtry nownot recorded
2026-08-058.59.593,187lowtry nownot recorded
2026-08-048.53.692,863lowtry nowslowing
2026-08-038.53.692,863lowtry nowslowing
2026-08-028.53.692,777lowtry nowslowing

Why the record changed

stars changed

Stars changed: 93731 → 93805.

stars changed

Stars changed: 93644 → 93731.

stars changed

Stars changed: 93552 → 93644.

stars changed

Stars changed: 93480 → 93552.

stars changed

Stars changed: 93420 → 93480.

stars changed

Stars changed: 92863 → 93420.

stars changed

Stars changed: 93296 → 92863.

stars changed

Reconstructed from adjacent retained daily snapshots; no upstream cause is inferred. Stars changed: 93187 → 93296.

stars changed

Reconstructed from adjacent retained daily snapshots; no upstream cause is inferred. Stars changed: 92863 → 93187.

stars changed

Stars changed: 92777 → 92863.

stars changed

Stars changed: 92710 → 92777.

stars changed

Source-observed stars changed: 92684 → 92710. This reports the retained observation delta and does not infer why the upstream change occurred.