Week 43, 2026 · Oct 19 to Oct 25, 2026

New in week 43

Tools first seen in the catalog this week, newest first. Also as an Atom feed (or just models).

All types Connectors Skills Plugins Harnesses & SDKs Agents No-code builders Models Agent infrastructure Observability & evals Identity, auth & payments Templates Protocols & benchmarks Artifacts

Any grade Security A Security B Security C Security D Security FSecurity grades are being rolled out; most listings are not graded yet.

695 listings first seen Oct 19 to Oct 25, 2026

0.432score
DeepSeek-V3.2-Speciale
deepseek-ai
Open-weights 685.4B-parameter text model from deepseek-ai on Hugging Face (mit).
ModelDFreshness: DOpen weights
0.583score
DeepSeek-V4-Flash-DSpark
deepseek-ai
Open-weights 165.27B-parameter text model from deepseek-ai on Hugging Face (mit).
ModelCFreshness: COpen weights
0.497score
DeepSeek-V4-Pro-DSpark
deepseek-ai
Open-weights 1650.5B-parameter text model from deepseek-ai on Hugging Face (mit).
ModelCFreshness: COpen weights
0.462score
distilgpt2
distilbert
Open-weights 0.09B-parameter text model from distilbert on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.462score
dolphin-2.9.1-yi-1.5-34b
dphn
Open-weights 34.39B-parameter text model from dphn on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.462score
gpt-j-6b
EleutherAI
Open-weights 6B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.398score
gpt-neo-1.3B
EleutherAI
Open-weights 1.37B-parameter text model from EleutherAI on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.377score
gpt-neo-125m
EleutherAI
Open-weights 0.15B-parameter text model from EleutherAI on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.398score
gpt-neo-2.7B
EleutherAI
Open-weights 2.72B-parameter text model from EleutherAI on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.377score
gpt-neox-20b
EleutherAI
Open-weights 20.74B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.462score
pythia-1.4b
EleutherAI
Open-weights 1.52B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.508score
pythia-14m
EleutherAI
Open-weights 0.01B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights
0.462score
pythia-160m
EleutherAI
Open-weights 0.21B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.377score
pythia-160m-deduped
EleutherAI
Open-weights 0.21B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.462score
pythia-1b
EleutherAI
Open-weights 1.08B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.462score
pythia-410m
EleutherAI
Open-weights 0.51B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.377score
pythia-70m-deduped
EleutherAI
Open-weights 0.1B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.641score
Qwen3.8-4B-Distill
empero-ai
Open-weights 4.66B-parameter text model from empero-ai on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights
0.462score
gpt2-mini
erwanf
Open-weights 0.04B-parameter text model from erwanf on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.370score
MobileLLM-R1-950M
facebook
Open-weights 0.95B-parameter text model from facebook on Hugging Face (fair-noncommercial-research).
ModelFFreshness: FOpen weights
0.397score
opt-125m
facebook
Open-weights text model from facebook on Hugging Face (other).
ModelFFreshness: FOpen weights
0.397score
opt-350m
facebook
Open-weights text model from facebook on Hugging Face (other).
ModelFFreshness: FOpen weights
0.462score
Meta-Llama-3-8B-Instruct-abliterated-v3
failspy
Open-weights 8.03B-parameter text model from failspy on Hugging Face (llama3).
ModelFFreshness: FOpen weights
0.686score
OTel-2.0-LLM-31B-IT
farbodtavakkoli
Open-weights 31.27B-parameter text model from farbodtavakkoli on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.690score
OTel-2.0-LLM-31B-IT-QLoRA
farbodtavakkoli
Open-weights 31.27B-parameter text model from farbodtavakkoli on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.462score
transformer-1.3B-100B
fla-hub
Open-weights 1.36B-parameter text model from fla-hub on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.332score
functiongemma-270m-it
google
Open-weights 0.27B-parameter text model from google on Hugging Face (gemma).
ModelDFreshness: DOpen weights
0.371score
gemma-2-2b
google
Open-weights 2.61B-parameter text model from google on Hugging Face (gemma).
ModelFFreshness: FOpen weights
0.371score
gemma-2-2b-it
google
Open-weights 2.61B-parameter text model from google on Hugging Face (gemma).
ModelFFreshness: FOpen weights
0.320score
gemma-2-9b
google
Open-weights 9.24B-parameter text model from google on Hugging Face (gemma).
ModelFFreshness: FOpen weights
0.371score
gemma-2-9b-it
google
Open-weights 9.24B-parameter text model from google on Hugging Face (gemma).
ModelFFreshness: FOpen weights
0.371score
gemma-3-1b-it
google
Open-weights 1B-parameter text model from google on Hugging Face (gemma).
ModelFFreshness: FOpen weights
0.320score
gemma-3-270m
google
Open-weights 0.27B-parameter text model from google on Hugging Face (gemma).
ModelFFreshness: FOpen weights
0.320score
gemma-3-270m-it
google
Open-weights 0.27B-parameter text model from google on Hugging Face (gemma).
ModelFFreshness: FOpen weights
0.343score
gemma-3n-E2B-it-litert-lm
google
Open-weights text model from google on Hugging Face (gemma).
ModelDFreshness: DOpen weights
0.343score
gemma-3n-E4B-it-litert-lm
google
Open-weights text model from google on Hugging Face (gemma).
ModelDFreshness: DOpen weights
0.322score
medgemma-27b-text-it
google
Open-weights 27.01B-parameter text model from google on Hugging Face (health-ai-developer-foundations).
ModelFFreshness: FOpen weights
0.374score
t5gemma-2b-2b-ul2-it
google
Open-weights 5.6B-parameter text model from google on Hugging Face (gemma).
ModelFFreshness: FOpen weights
0.315score
vaultgemma-1b
google
Open-weights 1.04B-parameter text model from google on Hugging Face (gemma).
ModelFFreshness: FOpen weights
0.398score
Llama-3-8B-Instruct-Gradient-1048k
gradientai
Open-weights 8.03B-parameter text model from gradientai on Hugging Face (llama3).
ModelFFreshness: FOpen weights
0.462score
LLaDA-8B-Instruct
GSAI-ML
Open-weights 8.02B-parameter text model from GSAI-ML on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.462score
h2o-danube3-500m-chat
h2oai
Open-weights 0.51B-parameter text model from h2oai on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.438score
The_GuageLLM_23M
Hai929
Open-weights 0.02B-parameter text model from Hai929 on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights
0.373score
zephyr-7b-beta
HuggingFaceH4
Open-weights 7.24B-parameter text model from HuggingFaceH4 on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.462score
SmolLM2-135M
HuggingFaceTB
Open-weights 0.13B-parameter text model from HuggingFaceTB on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.462score
SmolLM2-360M
HuggingFaceTB
Open-weights 0.36B-parameter text model from HuggingFaceTB on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.462score
SmolLM3-3B
HuggingFaceTB
Open-weights 3.08B-parameter text model from HuggingFaceTB on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.462score
llama-7b
huggyllama
Open-weights 6.74B-parameter text model from huggyllama on Hugging Face (other).
ModelFFreshness: FOpen weights
0.398score
ALLaM-7B-Instruct-preview
humain-ai
Open-weights 7B-parameter text model from humain-ai on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.462score
granite-3.3-2b-instruct
ibm-granite
Open-weights 2.53B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights

The weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.