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

0.438score
granite-4.0-h-small
ibm-granite
Open-weights 32.21B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights
0.583score
granite-4.1-3b
ibm-granite
Open-weights 3.4B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelCFreshness: COpen weights
0.503score
granite-4.1-8b
ibm-granite
Open-weights 8.79B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelCFreshness: COpen weights
0.587score
granite-switch-4.1-30b
ibm-granite
Open-weights 29.99B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.587score
granite-switch-4.1-8b
ibm-granite
Open-weights 8.78B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.593score
K2-Horizon-3.7B
IFM
Open-weights 5.06B-parameter text model from IFM on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.593score
K2-Horizon-375B-A23B
IFM
Open-weights 379.17B-parameter text model from IFM on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.568score
K2-Horizon-7B
IFM
Open-weights 9B-parameter text model from IFM on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.593score
K2-Horizon-MoVA-36B-A4B
IFM
Open-weights 37.44B-parameter text model from IFM on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.462score
saiga_llama3_8b
IlyaGusev
Open-weights 8.03B-parameter text model from IlyaGusev on Hugging Face (llama3).
ModelFFreshness: FOpen weights
0.547score
Ling-1T
inclusionAI
Open-weights 999.71B-parameter text model from inclusionAI on Hugging Face (mit).
ModelBFreshness: BOpen weights
0.547score
Ling-2.6-1T
inclusionAI
Open-weights 1025.41B-parameter text model from inclusionAI on Hugging Face (mit).
ModelBFreshness: BOpen weights
0.547score
Ling-2.6-flash
inclusionAI
Open-weights 107.49B-parameter text model from inclusionAI on Hugging Face (mit).
ModelBFreshness: BOpen weights
0.587score
Ling-3.0-flash-Sante
inclusionAI
Open-weights 127.49B-parameter text model from inclusionAI on Hugging Face (mit).
ModelAFreshness: AOpen weights
0.587score
Ling-3.0-flash-UBTree
inclusionAI
Open-weights 0.48B-parameter text model from inclusionAI on Hugging Face (mit).
ModelAFreshness: AOpen weights
0.587score
Ling-3.1-flash
inclusionAI
Open-weights 572.12B-parameter text model from inclusionAI on Hugging Face (mit).
ModelAFreshness: AOpen weights
0.508score
LLaDA2.0-mini
inclusionAI
Open-weights 16.26B-parameter text model from inclusionAI on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights
0.641score
Qwen3.8-27B-DFlash2
incoai
Open-weights 1.92B-parameter text model from incoai on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights
0.551score
Agents-A1
InternScience
Open-weights 35.11B-parameter text model from InternScience on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights
0.641score
gemma4-e4b-claims-comparison
k-chirkunov
Open-weights 7.94B-parameter text model from k-chirkunov on Hugging Face (gemma).
ModelBFreshness: BOpen weights
0.681score
glm-5.3-exlr8-k2-k3-k4
kindlingai
Open-weights text model from kindlingai on Hugging Face (glm-5.3).
ModelAFreshness: AOpen weights
0.553score
KAT-Coder-V2.5-Dev
Kwaipilot
Open-weights 34.66B-parameter text model from Kwaipilot on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights
0.398score
EXAONE-3.0-7.8B-Instruct
LGAI-EXAONE
Open-weights 7.82B-parameter text model from LGAI-EXAONE on Hugging Face (exaone).
ModelFFreshness: FOpen weights
0.508score
EXAONE-3.5-7.8B-Instruct
LGAI-EXAONE
Open-weights 7.82B-parameter text model from LGAI-EXAONE on Hugging Face (exaone).
ModelDFreshness: DOpen weights
0.553score
K-EXAONE-236B-A23B
LGAI-EXAONE
Open-weights 237.1B-parameter text model from LGAI-EXAONE on Hugging Face (k-exaone).
ModelBFreshness: BOpen weights
0.583score
kimi-k2.6-eagle3-mla
lightseekorg
Open-weights 3.02B-parameter text model from lightseekorg on Hugging Face (other).
ModelCFreshness: COpen weights
0.553score
LFM2-1.2B
LiquidAI
Open-weights 1.17B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights
0.547score
LFM2-2.6B-Exp
LiquidAI
Open-weights 2.57B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights
0.522score
LFM2-24B-A2B
LiquidAI
Open-weights 23.84B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights
0.528score
LFM2-8B-A1B
LiquidAI
Open-weights 8.34B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights
0.641score
LFM2.5-1.2B-Instruct
LiquidAI
Open-weights 1.17B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights
0.547score
LFM2.5-1.2B-Thinking
LiquidAI
Open-weights 1.17B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights
0.553score
LFM2.5-230M
LiquidAI
Open-weights 0.23B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights
0.583score
LFM2.5-230M-Base
LiquidAI
Open-weights 0.23B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelCFreshness: COpen weights
0.553score
LFM2.5-350M
LiquidAI
Open-weights 0.35B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights
0.553score
LFM2.5-8B-A1B
LiquidAI
Open-weights 8.47B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights
0.462score
llm-jp-3-150m
llm-jp
Open-weights 0.15B-parameter text model from llm-jp on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.398score
vicuna-7b-v1.5
lmsys
Open-weights 7B-parameter text model from lmsys on Hugging Face (llama2).
ModelFFreshness: FOpen weights
0.393score
TinyLLama-v0
Maykeye
Open-weights text model from Maykeye on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.398score
LongCat-Flash-Chat
meituan-longcat
Open-weights 561.86B-parameter text model from meituan-longcat on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.593score
MemT-1.0-Flash
MemTensor
Open-weights 287.94B-parameter text model from MemTensor on Hugging Face (mit).
ModelAFreshness: AOpen weights
0.593score
MemT-1.0-Nano
MemTensor
Open-weights 35.11B-parameter text model from MemTensor on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.462score
Llama-2-13b-chat-hf
meta-llama
Open-weights 13.02B-parameter text model from meta-llama on Hugging Face (llama2).
ModelFFreshness: FOpen weights
0.398score
Llama-2-13b-hf
meta-llama
Open-weights 13.02B-parameter text model from meta-llama on Hugging Face (llama2).
ModelFFreshness: FOpen weights
0.392score
Llama-2-70b-chat-hf
meta-llama
Open-weights 68.98B-parameter text model from meta-llama on Hugging Face (llama2).
ModelFFreshness: FOpen weights
0.398score
Llama-2-70b-hf
meta-llama
Open-weights 68.98B-parameter text model from meta-llama on Hugging Face (llama2).
ModelFFreshness: FOpen weights
0.392score
Llama-2-7b
meta-llama
Open-weights 7B-parameter text model from meta-llama on Hugging Face (llama2).
ModelFFreshness: FOpen weights
0.462score
Llama-2-7b-chat-hf
meta-llama
Open-weights 6.74B-parameter text model from meta-llama on Hugging Face (llama2).
ModelFFreshness: FOpen weights
0.462score
Llama-2-7b-hf
meta-llama
Open-weights 6.74B-parameter text model from meta-llama on Hugging Face (llama2).
ModelFFreshness: FOpen weights
0.398score
Llama-3.1-405B
meta-llama
Open-weights 405.85B-parameter text model from meta-llama on Hugging Face (llama3.1).
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.