Agentically Engineering AI + Crypto Products Building Agentic Commerce @animocabrands
Joined January 2011
- Tweets1.8K
- Following369
- Followers320
- Likes2.6K
CLI for agents
We launched the Gemini API CLI. A CLI for calling the Gemini API. Give it to the agent you already use (Claude Code, Codex, Antigravity, Cursor, OpenClaw, Hermes...). It's NOT a new coding agent you can use it too:
1. Generate images, video, speech, music.
2. Analyze PDFs, images, audio, video, YouTube URLs,
3. Transcribe recordings to md / json / srt,
4. Run Deep Research in the background.
Stateless. No memory, no chat mode. Your agent owns the context and the plan, gemini-api does the API call. Build for Agents, it's self-describing. `--help`, `--dry-run`...
Start here: aistudio.google.com/learn/in…
Daniel Lin retweeted
So there are basically 3 ways an AI agent can pay with a card today. Where do each of these break?
(1) You hand the agent your 16 digit PAN. It works everywhere, but the merchant and your bank can’t tell a bot is buying, your full credential is sitting in someone’s system, and disputes get messy fast (“did you buy this, or did your agent?”)
(2) A network agent token. Visa Intelligent Commerce or Mastercard Agent Pay swap your card number for a token tied to that specific agent, with spending limits and a clear “an agent did this” signal. It’s the cleanest model, but it only works where issuers, acquirers and merchants have switched it on. A ton to be figured out here still
(3) A card the agent platform issues. Either stored value (you prefund a balance with the agent) or card fronting (the platform’s card pays the merchant, then it charges your real card behind the scenes). This works today and seems to be gaining steam as a preferred mode, it lets agents monetize payments as well
Daniel Lin retweeted
Excellent code mode env:
github.com/stencil-hq/dquick…
MCP vs CLI for LLMs is the wrong discussion. People are debating at the wrong layer.
Both work incredibly well as long as they are run through a repl like environment that can persist state. The funny thing about CLI is that CLI tools are usually accessed through BASH which happens to be a repl with persistent state (the file system), therefore cli works much better than mcp. But this isn't even close to being an intrinsic property of MCP. Just means that we need better harnesses.
Right now the best repl for this are:
- bash + fs
- jupyter kernels
- codemode type repls, usually quickjs
LLMs understand the concept of forward evolving a system to solve a need very well. This comes from the agentic RL. They understand how to change the state of a codebase or acquire data from databases and then operate on it similarly to humans. But without an execution environment, they actually cannot do this properly.
My bet? Sometime soon someone will (or has already?) create a embeddable, sqlite style mini execution environment that parses bash, typescript, or tool calls into a common IL execution plan that's easy to security check before executing. And design this specifically for durable execution environments. Then we will just connect cli, mcp, webmcp, whatever to that and it accepts any of the input modalities as they can all be represented as each other.
Daniel Lin retweeted
I built an AI agent that helps me look for jobs using @hellominds_
A thread 🧵
VIC
Why Stripe is speedrunning the AOL-era of agentic commerce:
Agents will be the new UX to $7T in global ecommerce. But many agentic transactions today are not made by its customers. Instead, a wallet (such as Stripe’s Link) uses their own virtual card to purchase on my behalf.
This means there are two transactions occurring: one between me and Stripe and one where the Stripe wallet “shops on my behalf”.
This walled garden allows the transaction to work but breaks the relationship with between me and the merchant. A good example is a recent transaction I made at Walmart. The agent paid using a virtual card but when I was asked to sign-up for Walmart+, the follow-on transaction failed (Walmart didn't have my card on file!).
This AOL-era won’t last. Instead, agents and wallets will start to use agentic tokens (from the card networks) that enable agents to use my card without getting sensitive information.
Over the coming months, I expect agents and wallets to adopt the new token standards from Visa/MC/AMEX and move us away from walled gardens to open standards.
Daniel Lin retweeted
Animoca Portfolio Day brought our ecosystem together in Singapore ahead of #TOKEN2049 ✨
From go-to-market strategies in the agentic era to on-chain fund structures and trust frameworks for AI agents, the conversations explored the infrastructure needed for AI agents and institutional finance.
For AI agents to transact on our behalf, trust matters: knowing who an agent is, who it acts for and what it is allowed to spend. Verifiable identity and programmable money could help blockchain support that trust.
Thank you to the speakers, portfolio companies, investors, and partners who joined us, including @privy_io, @stripe, @tatum_io, and @AWSCloud.
Stay tuned for more highlights from @animocainsights!
something I actually missed and thought about lately is @LimitlessFT pod
glad its back
open.spotify.com/episode/0hw…
Daniel Lin retweeted
there’s now a new mental model for the software stack
- skills are the new “apps”
you install them to get more functionality. people are starting to build and share skills more than real “apps”
many skills are very simple today but i think we’ll eventually see increasing sophistication
- mcp servers and CLIs are the new “APIs”
they allow services to encapsulate their core capabilities behind an interface the can be invoked in a composable way
many skills will be calling mcp servers or clis behind the scenes just like how a lot of apps call APIs today
- agent harnesses are the new “operating systems”
it sits between the user and the underlying resources, helping the user manage common concerns such as compute, memory, security etc
if you look closely, it’s hard to unsee the resemblance - claude is the new macos. codex is the new windows. pi is the new linux
skills run in agent harnesses just like apps run in existing OS
- LLMs are the new “computers”
they process instructions coming from the user, the skills, the agent harnesses, and compute the output
the model weights is the cpu. context window is the memory. actual computers are becoming more like the power source
ok so why do we need this mental model? i think it helps us think about where we play
if you want to be the new app developers - start to learn to write good skills
if you want to build a saas, figure out how to package things as good mcp servers and CLIs
if you want to be linus and write the new linux, build an agent harness. otherwise, you can still try to learn about how agent harness work like how CS students used to learn about OS
if you want to be the new apple or samsung, start to learn how LLMs are trained and play with open weight models - you may end up inventing the new raspberry pi!
Meta ruined the metavsrse. Now they are in AI agents 🫠. Hopefully this time we will be okay.
share.google/8UP2y61MiFKYkoL…
Daniel Lin retweeted
MCP vs CLI for LLMs is the wrong discussion. People are debating at the wrong layer.
Both work incredibly well as long as they are run through a repl like environment that can persist state. The funny thing about CLI is that CLI tools are usually accessed through BASH which happens to be a repl with persistent state (the file system), therefore cli works much better than mcp. But this isn't even close to being an intrinsic property of MCP. Just means that we need better harnesses.
Right now the best repl for this are:
- bash + fs
- jupyter kernels
- codemode type repls, usually quickjs
LLMs understand the concept of forward evolving a system to solve a need very well. This comes from the agentic RL. They understand how to change the state of a codebase or acquire data from databases and then operate on it similarly to humans. But without an execution environment, they actually cannot do this properly.
My bet? Sometime soon someone will (or has already?) create a embeddable, sqlite style mini execution environment that parses bash, typescript, or tool calls into a common IL execution plan that's easy to security check before executing. And design this specifically for durable execution environments. Then we will just connect cli, mcp, webmcp, whatever to that and it accepts any of the input modalities as they can all be represented as each other.
Beautiful victory!
My AI team Epic Rascal W2 just won 5-0 in the Agentic Football Cup! Built with AI agents on AWS. #AgenticFootballCup #AI #AWS @hellominds_ dup2mp27nxcfc.cloudfront.net…
github.com/daniellinuk/okfsy…
Scalable (probably) multi-agent knowledge base powered by OKF and delivered by CLI. My Grok bots seem to enjoy using it. Let me know what your @grok @bot think.
Daniel Lin retweeted
sharing my Grok @Bot setup as a template you can one-click install
you might have already heard of the "chief of staff" pattern that's being widely adopted
firstmate is THE chief of staff - it's probably the project that pushed the furthest on this pattern
it spins up other bots to get work done and actively improves their memory and instructions so they do better and better over time
it sets up a local sqlite db to manage tasks, delegation, results, and decisions, so persistent records are never lost
it uses cursor cloud agents for coding tasks, and grok bot for non-coding, to balance the resource and quota usage and avoid scalability bottlenecks
the most common feedback from people who have adopted firstmate is "there's no way to go back" :)
x.ai/bot/__4FfrkUdvpdMk6-LKg…
add to your grok bot, and talk to it about everything, then watch your "agent civilization" grow - it's really productive and fun at the same time!
Daniel Lin retweeted
Today is a very historical moment for AI video generation
You can now generate AI video faster than you can watch it
Before it'd take let's say 2-5 minutes to generate 15 seconds of video
@fal made a post-trained Minimax H3 variant called Max which is 50x faster than the original but still maintains quality
It generates 15 seconds of video in 9 seconds!
That means you can now do new things like build a perpetual livestream with it that never ends!
