Builders 🚀 You can now experiment with GLM models inside AdaL CLI with free access.
@ZaiforStartups7.5K followers
37,774 views
39 Comments
Comments from the original post on X (Twitter)

@ZaiforStartups
Looking forward to see your projects with GLM.
13 likes

@neural_avb
this convinces me that Zai are also working on a video generation model
12 likes

@ZaiforStartups
Haha you might be onto something 👀
8 likes

@panda_liyin
Thanks for highlighting our coding agent. You can check it out at
6 likes

@maxjendrall
Video is surely not AI generated
6 likes

@SamadderSignal
I have applied but haven’t received any response
3 likes

@ZaiforStartups
Thanks for applying! We're reviewing applications and feel free to DM us.👀
2 likes

@iamsubha44
Providing free GLM models in AdaL CLI from @ZaiforStartups grants rare multi-model flexibility within a workflow-centric agent. Combined with persistent memory, it positions startups to iterate rapidly without common agent limitations.
2 likes

@AbuKhadeejah
Advantages over kilo ?
1 like

@ZaiforStartups
Good question. Feel free to try it and let us know how it compares.
2 likes

@AbuKhadeejah
Soon on a new project.

@agentxagi
Long-term memory for coding agents is what separates a useful tool from a true developer partner. An agent that remembers your architecture decisions, naming conventions, and past mistakes from 3 months ago is infinitely more valuable than one that starts fresh every session.
1 like

@VibeCoderOfek
AdaL CLI with GLM is a backend dev's dream long-term memory means less context loss in complex builds. Testing it on my API project now! 🔥
1 like

@trungking
Applied and wait for week without any response or email. At least vibe code a dashboard to let everyone know the status
1 like

@ardiPseptiadi
Cool. Wanna try it after pony-alpha-2 testing 🙊
1 like

@saiharsha008
I’m still being charged for GLM-5 even though it’s supposed to be free this month. Can someone please check this and fix the issue?

@askgpts
Woww

@vyviid
real speed comes from persistent memory across sessions, not just switching models. context gets lost when memory is not scoped to the project. try the same refactor across three sessions and check which details survive.

@senthazalravi
Applied

@Lakshman2302
I'm building for students
















