Joined October 2024
- Tweets 353
- Following 17
- Followers 2,199
- Likes 1,290
12 Photos and videos
Codebuff retweeted
Jun 12
Our free coding agent used 124 billion tokens of DeepSeek V4 Pro in May. That's a lot!
In 11 days of June, it's already used 184 billion 🤯
Try it free: npm i -g freebuff
20
6
171
13,865
Codebuff retweeted
Jun 10
In our free coding agent, MiniMax M3 usage has been gaining.
But it's still behind DeepSeek V4 Pro
Use 100% free: npm i -g freebuff
41
21
483
29,090
Codebuff retweeted
Jun 9
Our coding agent now has MiniMax M3 with unlimited* free usage!
*Up to 4,000 agent steps per day
Try it: npm i -g freebuff
22
12
299
17,310
Codebuff retweeted
Jun 8
We just added a lot more models to our 100% free coding agent.
Try the new MiniMax M3 or MiMo 2.5 Pro 🔥
It's free: npm i -g freebuff
58
66
612
40,012
Codebuff retweeted
May 25
Stop paying for coding agents.
Freebuff gives you DeepSeek V4 Pro completely free.
Choose from the best open-source models, with 5 free sessions per day.
npm i -g freebuff
37
24
330
28,472
Codebuff retweeted
May 23
This is the most live users we've ever had.
All around the world, people are using our free coding agent, with mostly DeepSeek models!
32
5
153
9,583
Codebuff retweeted
May 22
DeepSeep V4 Pro will remain 100% free in our coding agent 🎉
Try it now:
npm i -g freebuff
May 22
We are making our discount permanent! 🎉
Enjoy building with DeepSeek-V4-Pro and bring your innovative ideas to life! 🚀
113
185
2,927
289,240
Codebuff retweeted
May 21
We just overhauled our web search, with subagents!
1. The main agent spawns a researcher with a prompt
2a. Researcher does web searches
2b. Researcher reads specific URLs for more depth
2c. Researcher outputs a complete answer
Simple, but keeps the main agent context clean
4
3
41
3,380
Codebuff retweeted
May 19
Our 100% free coding agent is growing very rapidly!
Try it now:
npm i -g freebuff
11
3
86
8,892
Codebuff retweeted
May 15
We just launched our 100% free coding agent everywhere.
Every person in the world has access to 5 free hours of DeepSeek V4 Flash, everyday.
npm i -g freebuff
94
52
754
54,522
Codebuff retweeted
May 12
Introducing a 100% free coding agent with DeepSeek v4 Pro
Choose any model, all free:
- DeepSeek v4 Pro/Flash
- Kimi K2.6
- MiniMax M2.7
npm i -g freebuff
317
415
3,773
398,206
Codebuff retweeted
Apr 22
Incredible. We're moving the opposite way.
Try our completely free coding agent using open source models! npm i -g freebuff
Apr 21
Anthropic just pulled Claude Code from the Pro plan.
Pro users wanting it need Max now.
$100/month minimum. 5x jump.
I'm on Max 20x so I'm fine.
Flagging for anyone on Pro who's about to find out.
No announcement. Just a pricing page edit.
5
2
37
4,312
Codebuff retweeted
Apr 21
Just launched this: choose which model you want to use!
Both choices are free, but GLM has a longer wait.
Stay tuned -- Kimi K2.6 is coming soon!
25
5
118
7,887
Codebuff retweeted
Apr 20
We just launched a waiting room for our free coding agent.
Once admitted, you get 1 hour of unlimited usage of GLM 5.1
Try it: npm i -g freebuff
30
4
116
10,973
Codebuff retweeted
Apr 16
This is the most usage we've ever had.
People really wanted a free coding agent with GLM 5.1.
14
1
88
6,177
Codebuff retweeted
Apr 16
We just switched our free coding agent to use GLM 5.1 instead of MiniMax M2.5
Eval performance went from 68% to 83% 🔥
P.S. It's still 100% free
npm install -g freebuff
58
21
576
60,414
Codebuff retweeted
Apr 1
There was some confusion when we launched Freebuff, the free coding agent.
How does it compare to @CodebuffAI?
To make the difference clearer, Codebuff is rebranding to Expensivebuff! 🥳💸💰
Enjoy: npm i -g expensivebuff
3
1
28
2,528
Codebuff retweeted
Mar 20
Introducing Freebuff: the free coding agent
100% free, up to 10x as fast as Claude Code
npm install -g freebuff
125
78
806
126,023
Codebuff retweeted
Mar 4
We upgrade our file picker agent to use Gemini 3.1 Flash Lite!
It's 4x faster than Grok 4.1 Fast was.
Gemini 3.1 Flash-Lite has landed.
It’s our most cost-efficient Gemini 3 series model yet, built for intelligence at scale. Here’s what’s new 🧵
1
3
30
4,153