Python · AGPL-3.0
p-e-w/heretic
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
★ 39.5k
Stars
4.5k forks · 63 open issues
+346/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
89.3
Momentum / 100
see the breakdown below
13mo ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 48.6 | +346/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 12.4 | last week ran 1.82× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 13.3 | 39.5k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 89.3 | sum of the above |
Detail
| Topics | abliterationanti-censorshipanticensorshipcensorshipcensorship-resistancellmtransformer |
| Matched on | LLM & Inference (llm) |
| Short window | +2.4k stars over 7 days = 346.4/day |
| Long window | +4.9k stars over 26 days = 189.9/day |
| Lifetime average | 96.18 stars/day over 410 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |