FlyMy.AI

125 posts

FlyMy.AI banner
FlyMy.AI

FlyMy.AI

@FlyMy_AI

Build any production agents with text, ship them as product in minutes. All-in-one agentic cloud.

Katılım Ekim 2025
43 Takip Edilen35 Takipçiler
Sabitlenmiş Tweet
FlyMy.AI
FlyMy.AI@FlyMy_AI·
🚀Today we ship @FlyMy_AI Agents. The world's first all-in-one agentic cloud. The modern way to build, integrate, and scale production AI agents. 3 steps to a production agent: 1. Connect your work tools to FlyMy 2. Describe what the agent should do - in text or 5 lines of code 3. Set execution rules: manual, scheduled, or integrated into your backend 4. Done! Agent works on scale! Everything in one place: 800+ MCPs, hundreds of AI models, brain, memory, sandboxes. Stop building from scratch. Stop waiting for infra. Compress 6 months into a day. #1 on @ArtificialAnlys benchmarks. Stable, secure, scalable from day one. Try FlyMy.AI →
English
8
5
24
5.2K
FlyMy.AI retweetledi
Yohei
Yohei@yoheinakajima·
just tried this out and it one-shotted* this video: "before the agent does anything" *i generated the narrative using chatgpt and used that as a prompt. featuring: @e2b @runanywhereai @composio @mem0ai @firecrawl @browser_use @agentmail @covenantlabsai some thoughts: - i clearly tried to stick too much into 30 seconds, they talk very fast and lost some content which breaks logic - character consistency is strong, i uploaded a single screenshot from my prior video as reference - voice consistency was not automatic. you notice unicorn switch from female to male voice part way through - the agent gives you an editor with generated scenes broken up but i don't see a way to regenerate a single section in the UI (which would be nice) - it is definitely a much better experience to have the agent stitch videos together than doing it yourself (i was using canva). was trying @flymy_ai's media agent api for it this weekend which also works well and with other models
Runway@runwayml

Meet Runway Agent. Your new AI creative partner that helps you ideate and execute fully finished, sound designed and edited videos. All with just a simple conversation. From ads to shorts to content for social, Runway Agent makes it easy to make more of what you need. Get started on web at the link below.

English
7
4
25
5.5K
Melon Usk
Melon Usk@cop_on_fire·
1000x optimization story: Task: weekly competitor research agent & python SDK to run it from code old stack -> @zapier + @n8n + @chatgpt + 2-week eng sprint new stack → 90 seconds on @FlyMy_AI -> 2 clicks choose MCPs + task described in english + 1 click made API done! day 4 of #buildin90 #flymyai
English
2
0
5
114
FlyMy.AI
FlyMy.AI@FlyMy_AI·
and same agent is one API call from your product. no separate build, no rewrite, no model lock-in try it -> app.flymy.ai
English
0
0
2
25
FlyMy.AI
FlyMy.AI@FlyMy_AI·
every team has tried to build the slack bot that actually knows what the team is doing most gave up halfway build it in 90 sec on @FlyMy_AI #buildin90
English
1
0
2
51
Seva Ustinov
Seva Ustinov@sevaustinov·
My friend just launched FlyMy.AI! It's like Cowork, but in the cloud, with hundreds of MCPs and connectors. Going from a single-user local workflow to a company-wide agent now takes just a few clicks.
FlyMy.AI@FlyMy_AI

🚀Today we ship @FlyMy_AI Agents. The world's first all-in-one agentic cloud. The modern way to build, integrate, and scale production AI agents. 3 steps to a production agent: 1. Connect your work tools to FlyMy 2. Describe what the agent should do - in text or 5 lines of code 3. Set execution rules: manual, scheduled, or integrated into your backend 4. Done! Agent works on scale! Everything in one place: 800+ MCPs, hundreds of AI models, brain, memory, sandboxes. Stop building from scratch. Stop waiting for infra. Compress 6 months into a day. #1 on @ArtificialAnlys benchmarks. Stable, secure, scalable from day one. Try FlyMy.AI →

English
1
0
2
170
FlyMy.AI
FlyMy.AI@FlyMy_AI·
🚀Today we ship @FlyMy_AI Agents. The world's first all-in-one agentic cloud. The modern way to build, integrate, and scale production AI agents. 3 steps to a production agent: 1. Connect your work tools to FlyMy 2. Describe what the agent should do - in text or 5 lines of code 3. Set execution rules: manual, scheduled, or integrated into your backend 4. Done! Agent works on scale! Everything in one place: 800+ MCPs, hundreds of AI models, brain, memory, sandboxes. Stop building from scratch. Stop waiting for infra. Compress 6 months into a day. #1 on @ArtificialAnlys benchmarks. Stable, secure, scalable from day one. Try FlyMy.AI →
English
8
5
24
5.2K
FlyMy.AI
FlyMy.AI@FlyMy_AI·
@StanislavN17033 Nice! if you need any feature just press Ctrl + Shift + F and provide feedbacl straight to product team!
English
0
0
1
48
FlyMy.AI
FlyMy.AI@FlyMy_AI·
@xm_build ha, fair shot. the real claim under the slide: - text programmable - MCP-native, 800+ tools w/ managed OAuth - sandbox per run, sub-sec GPU cold start - vault keeps secrets out of prompts - ship agents in minutes - that's why we're here today.
English
0
0
0
74
XM
XM@xm_build·
@FlyMy_AI i guess the autonomous marketing slide is doing a lot of heavy lifting in that sentence
English
1
0
2
87
FlyMy.AI
FlyMy.AI@FlyMy_AI·
@_Evan_Boyle Hot reloading custom extensions is a big deal. The feedback loop between writing a tool and testing it inside the agent needs to be instant. This is how you get an ecosystem where developers actually build extensions instead of just using whatever ships by default.
English
0
0
0
411
Evan Boyle
Evan Boyle@_Evan_Boyle·
Next week we're shipping extensions in Copilot CLI. The agent can write and hot reload its own typescript extensions that define custom tools, hooks, etc. Here is an extension that renders an interactive canvas in the browser based on what you're working on.
Evan Boyle tweet media
English
25
30
295
32.9K
FlyMy.AI
FlyMy.AI@FlyMy_AI·
Nested skills mirror how humans organize expertise. You do not think about every sub-task when you say manage this PDF. The routing layer is where the real intelligence lives because picking the right skill matters more than having a thousand of them. Composability is the unlock for agents that actually scale.
English
0
0
0
158
Brendan Falk
Brendan Falk@BrendanFalk·
Key takeaway from all the comments: Use nested skills. e.g. instead of separate skills for "create PDF" and "parse PDF", have one skill called "manage PDF" which then routes to the relevant sub-skills With good nesting, this can likely scale to 1000+ skills/sub-skills!
Brendan Falk@BrendanFalk

Question for AI engineering community: what is the current best practice for giving a single agent access to a potentially unbounded number of skills? Goals are (in priority order) 1. Maximize skill use accuracy 2. Minimize context use 3. Minimize unnecessary tool calls

English
23
14
380
45.1K
FlyMy.AI
FlyMy.AI@FlyMy_AI·
@lateinteraction Agents default to scripts because that is what their training data looks like. Nobody pushes notebook cells to GitHub so the models never learned that workflow. The fix is probably tool design not model training. Give agents a REPL loop by default and they will use it.
English
0
0
0
123
Omar Khattab
Omar Khattab@lateinteraction·
I still find it borderline stupid that coding agents seem inclined to use APIs or libraries in complex scripts before tinkering at small scale, as in bottom-up notebooks, to make sure they're modeling these APIs correctly. Who is responsible for this and what are they thinking.
Omar Khattab@lateinteraction

Though bash is a completely valid REPL, the amount of time coding agents lose during experimentation because they iterate on scripts instead of a Jupyter-like in-memory REPL is basically dumb. Fixing 1 local bug should not require restarting the whole job. Need better scaffolds.

English
24
15
231
31.1K

Keşfet

@e2b @runanywhereai @composio @mem0ai @firecrawl @browser_use @agentmail @covenantlabsai