CO

CogVLM

Multimodal AI·application·open·#747 of 886·+95·applications·Rising

60.7

Low

High confidence
WebsiteGitHub

Powerful open-source visual language model by Tsinghua University.

Pillar Breakdown

Adoption

35%

50.4

Maintenance

30%

65.5

Friction

20%

98.9

Ecosystem

15%

39.2

Momentum

0.46Rising
7d change +0.14
High confidence

In Multimodal AI

Ranked #15 of 18

1MediaPipe
82.6
2LLaMA-Factory
82.0
3serve
80.9
4rerun
75.7
5LLaVA
73.1
6LAVIS
72.2
7InternVL
70.0
8neuraltalk
69.3
See all 18 in Multimodal AI →

Similar Tools

OF

open_flamingo

Multimodal AI

60.7

DO

docarray

Multimodal AI

58.6

VL

VLM2Vec

Multimodal AI

57.0

M4

MiniGPT-4

Multimodal AI

66.2