Category: Gemini CLI

A bird's-eye view of a winding river of glowing green GitHub contribution tiles flowing across a dark landscape, with bright yellow-green flames rising from clusters of the brightest tiles, while a lone figure sits at a laptop at the edge of the mosaic under a distant skyline of code-filled windows.

4255 Contributions – A Year of Building in the Open

Allen Hutchison3 Comments

I was staring at my GitHub profile the other day when a number caught my eye. 4,255. That’s how many contributions GitHub has recorded for me over the past year. I sat with it for a moment, doing the quick mental math: that’s close to twelve contributions every single day, weekends included. The shape of the year looked just as striking. I showed up on 332 of the 366 days in the window, 91% of them, and at one point put together a 113-day streak without a gap. It felt like a lot. It felt like proof of something I hadn’t been able to articulate until I saw it rendered as a green heatmap on a screen.

About a year ago, I wrote about my decision to move back to individual contributor work after years in leadership roles. I talked about missing the flow state, the direct feedback loop of writing code and watching it work. What I didn’t know at the time was just how dramatically that shift would show up in the data. 4,255 contributions is the quantitative answer to the question I was trying to answer qualitatively in that post: what happens when you give a builder back the time to build?

The Shape of a Year

Numbers by themselves are just numbers. What makes them interesting is the shape they take when you zoom in. My year wasn’t a single monolithic effort on one project. It was a constellation of interconnected work, each project feeding into the next, each one teaching me something that made the others better.

The largest body of work was on Gemini CLI, Google’s open-source AI agent for the terminal. This project alone accounts for a significant chunk of those contributions, spanning everything from core feature development to building the Policy Engine that governs how the agent interacts with your system. But the contributions weren’t just code. A huge portion of my time went into code reviews, issue triage, and community engagement. Working on a repository with over 100,000 stars means that every merged PR has real impact, and every review is a conversation with developers around the world.

Then there was Gemini Scribe, my Obsidian plugin that started as a weekend experiment and grew into a tool with 302 stars and a community of writers who depend on it. Over the past year, I shipped a major 3.0 release, built agent mode, and iterated constantly on the rewrite features that make it useful for daily writing. In fact, this very blog post was drafted in the tool I built, which is a strange and satisfying loop.

Alongside these larger efforts, I shipped a handful of small, sharp tools that I needed for my own workflows. The GitHub Activity Reporter is one I’ve written about before, a utility that uses AI to transform raw GitHub data into narrative summaries for performance reviews and personal reflection. More recently, I built the Workspace extension for Gemini CLI and a deep research extension that lets you conduct multi-step research from the terminal. Each of these tools was born from a specific itch, and each turned out to be useful to more people than I expected. The Workspace extension alone has gathered 510 stars.

The Rhythm of Building

One thing the contribution graph doesn’t capture is the rhythm behind the numbers. My weeks developed a cadence over the year that I didn’t plan but that emerged naturally. Mornings were for deep work on Gemini CLI, the kind of focused system design and implementation that benefits from a fresh mind. Afternoons were for reviews and community work, responding to issues, providing feedback on PRs, and engaging with the developers building on top of our tools. Evenings and weekends were where the personal projects lived: Gemini Scribe, the extensions, and whatever new idea was rattling around in my head.

This rhythm is something I couldn’t have had in my previous role. When your calendar is stacked with meetings from nine to five, the creative work gets squeezed into the margins. Now, the creative work is the whole page. That’s the real story behind 4,255 contributions. It’s not about productivity metrics or GitHub gamification. It’s about what happens when you align your time with the work that energizes you.

What Surprised Me

A few things caught me off guard when I looked back at the year.

First, the ratio of code to “everything else” wasn’t what I expected. I assumed the majority of my contributions would be commits. In reality, a massive portion was reviews, comments, and issue management. On Gemini CLI alone I logged 205 reviews over the year. This was especially true as my role on that project evolved from pure contributor to something closer to a technical steward. Reviewing a complex PR, asking the right questions, and helping someone refine their approach takes just as much skill as writing the code yourself. Sometimes more.

Second, the personal projects had more reach than I anticipated. When I wrote about building personal software, I was mostly thinking about tools I built for myself. But Gemini Scribe has real users who file real bugs and request real features. The Workspace extension took off because it solved a problem that a lot of Gemini CLI users were hitting. Building in the open means you discover an audience you didn’t know was there.

Third, and this is the one I keep coming back to, the year felt shorter than 4,255 contributions would suggest. Flow state compresses time. When you’re deep in a problem, hours feel like minutes. I remember entire weekends spent in the codebase that felt like an afternoon. That compression is, for me, the clearest signal that I made the right call in going back to IC work.

Fourth, and this is the one I never would have predicted until I charted it out: the weekend, not the weekday, turned out to be my most productive window by a wide margin. Saturdays averaged 14.7 contributions, Sundays 14.5, and Thursday, the day I’d have guessed was safest, came in last at 8.3. The busiest single day of the entire year was a Saturday, December 20, when I shipped 89 contributions into podcast-rag, rebuilding the web upload flow, adding episode management to the admin dashboard, and migrating email delivery over to Resend, all in one afternoon. I didn’t plan for the weekends to become the engine. They just did, because that’s where the personal projects live, and the personal projects are where the work is loudest, most direct, and most free of interruption. A day with no meetings on it, I’ve come to realize, is worth more than I ever gave it credit for.

Looking Forward

I don’t know what next year’s number will be, and I’m not particularly interested in making it bigger. The number is a side effect, not a goal. What I care about is continuing to work on problems that matter, in the open, with people who push me to think more clearly. The AI-first developer model I wrote about over a year ago is now just how I work every day. The agents I’m building are the collaborators I’m building with, and both keep getting better.

If you’re someone who’s been thinking about a similar shift, whether it’s moving back to IC work, contributing to open source, or just carving out more time for the work that lights you up, I’d encourage you to try it. You might be surprised by what a year of focused building can produce. I certainly was.

A photorealistic image shows an old wooden-handled hammer on a cluttered workbench transforming into a small, multi-armed mechanical robot with glowing blue eyes, holding various miniature tools.

Everything Becomes an Agent

Allen Hutchison2 Comments

I’ve noticed a pattern in my coding life. It starts innocently enough. I sit down to write a simple Python script, maybe something to tidy up my Obsidian vault or a quick CLI tool to query an API. “Keep it simple,” I tell myself. “Just input, processing, output.”

But then, the inevitable thought creeps in: It would be cool if the model could decide which file to read based on the user’s question.

Two hours later, I’m not writing a script anymore. I’m writing a while loop. I’m defining a tools array. I’m parsing JSON outputs and handing them back to the model. I’m building memory context windows.

I’m building an agent. Again.

(For those keeping track: my working definition of an “agent” is simple: a model running in a loop with access to tools. I explored this in depth in my Agentic Shift series, but that’s the core of it.)

As I sit here writing this in January of 2026, I realize that almost every AI project I worked on last year ultimately became an agent. It feels like a law of nature: Every AI project, given enough time, converges on becoming an agent. In this post, I want to share some of what I’ve learned, and the cases where you might skip the intermediate steps and jump straight to building an agent.

The Gravitational Pull of Autonomy

This isn’t just feature creep. It’s a fundamental shift in how we interact with software. We are moving past the era of “smart typewriters” and into the era of “digital interns.”

Take Gemini Scribe, my plugin for Obsidian. When I started, it was a glorified chat window. You typed a prompt, it gave you text. Simple. But as I used it, the friction became obvious. If I wanted Scribe to use another note as context for a task, I had to take a specific action, usually creating a link to that note from the one I was working on, to make sure it was considered. I was managing the model’s context manually.

I was the “glue” code. I was the context manager.

The moment I gave Scribe access to the read_file tool, the dynamic changed. Suddenly, I wasn’t micromanaging context; I was giving instructions. “Read the last three meeting notes and draft a summary.” That’s not a chat interaction; that’s a delegation. And to support delegation, the software had to become an agent, capable of planning, executing, and iterating.

From Scripts to Sudoers

The Gemini CLI followed a similar arc. There were many of us on the team experimenting with Gemini on the command line. I was working on iterative refinement, where the model would ask clarifying questions to create deeper artifacts. Others were building the first agentic loops, giving the model the ability to run shell commands.

Once we saw how much the model could do with even basic tools, we were hooked. Suddenly, it wasn’t just talking about code; it was writing and executing it. It could run tests, see the failure, edit the file, and run the tests again. It was eye-opening how much we could get done as a small team.

But with great power comes great anxiety. As I explored in my Agentic Shift post on building guardrails and later in my post about the Policy Engine, I found myself staring at a blinking cursor, terrified that my helpful assistant might accidentally rm -rf my project.

This is the hallmark of the agentic shift: you stop worrying about syntax errors and start worrying about judgment errors. We had to build a “sudoers” file for our AI, a permission system that distinguishes between “read-only exploration” and “destructive action.” You don’t build policy engines for scripts; you build them for agents.

The Classifier That Wanted to Be an Agent

Last year, I learned to recognize a specific code smell: the AI classifier.

In my Podcast RAG project, I wanted users to search across both podcast descriptions and episode transcripts. Different databases, different queries. So I did what felt natural: I built a small classifier using Gemini Flash Lite. It would analyze the user’s question and decide: “Is this a description search or a transcript search?” Then it would call the appropriate function.

It worked. But something nagged at me. I had written a classifier to make a decision that a model is already good at making. Worse, the classifier was brittle. What if the user wanted both? What if their intent was ambiguous? I was encoding my assumptions about user behavior into branching logic, and those assumptions were going to be wrong eventually.

The fix was almost embarrassingly simple. I deleted the classifier and gave the agent two tools: search_descriptions and search_episodes. Now, when a user asks a question, the agent decides which tool (or tools) to use. It can search descriptions first, realize it needs more detail, and then dive into transcripts. It can do both in parallel. It makes the call in context, not based on my pre-programmed heuristics. (You can try it yourself at podcasts.hutchison.org.)

I saw the same pattern in Gemini Scribe. Early versions had elaborate logic for context harvesting, code that tried to predict which notes the user would need based on their current document and conversation history. I was building a decision tree for context, and it was getting unwieldy.

When I moved Scribe to a proper agentic architecture, most of that logic evaporated. The agent didn’t need me to pre-fetch context; it could use a read_file tool to grab what it needed, when it needed it. The complex anticipation logic was replaced by simple, reactive tool calls. The application got simpler and more capable at the same time.

Here’s the heuristic I’ve landed on: If you’re writing if/else logic to decide what the AI should do, you might be building a classifier that wants to be an agent. Deconstruct those branches into tools, give the agent really good descriptions of what those tools can do, and then let the model choose its own adventure.

You might be thinking: “What about routing queries to different models? Surely a classifier makes sense there.” I’m not so sure anymore. Even model routing starts to look like an orchestration problem, and a lightweight orchestrator with tools for accessing different models gives you the same flexibility without the brittleness. The question isn’t whether an agent can make the decision better than your code. It’s whether the agent, with access to the actual data in the moment, can make a decision at least as good as what you’re trying to predict when you’re writing the code. The agent has context you don’t have at development time.

The “Human-on-the-Loop”

We are transitioning from Human-in-the-Loop (where we manually approve every step) to Human-on-the-Loop (where we set the goals and guardrails, but let the system drive).

This shift is driven by a simple desire: we want partners, not just tools. As I wrote back in April about waiting for a true AI coding partner, a tool requires your constant attention. A hammer does nothing unless you swing it. But an agent? An agent can work while you sleep.

This freedom comes with a new responsibility: clarity. If your agent is going to work overnight, you need to make sure it’s working on something productive. You need to be precise about the goal, explicit about the boundaries, and thoughtful about what happens when things go wrong. Without the right guardrails, an agent can get stuck waiting for your input, and you’ll lose that time. Or worse, it can get sidetracked and spend hours on something that wasn’t what you intended.

The goal isn’t to remove the human entirely. It’s to move us from the execution layer to the supervision layer. We set the destination and the boundaries; the agent figures out the route. But we have to set those boundaries well.

Embracing the Complexity (Or Lack Thereof)

Here’s the counterintuitive thing: building an agent isn’t always harder than building a script. Yes, you have to think about loops, tool definitions, and context window management. But as my classifier example showed, an agentic architecture can actually delete complexity. All that brittle branching logic, all those edge cases I was trying to anticipate: gone. Replaced by a model that can reason about what it needs in the moment.

The real complexity isn’t in the code; it’s in the trust. You have to get comfortable with a system that makes decisions you didn’t explicitly program. That’s a different kind of engineering challenge, less about syntax, more about guardrails and judgment.

But the payoff is a system that grows with you. A script does exactly what you wrote it to do, forever. An agent does what you ask it to do, and sometimes finds better ways to do it than you’d considered.

So, if you find yourself staring at your “simple script” and wondering if you should give it a tools definition… just give in. You’re building an agent. It’s inevitable. You might as well enjoy the company.

A laptop sits on a dark wooden desk under the warm glow of an Edison bulb; above the screen, a stream of glowing, holographic research papers and data visualizations cascades downward like a waterfall, physically dissolving into lines of green and white markdown text as they enter the open terminal window.

Bringing Deep Research to the Terminal

Allen Hutchison1 Comment

I lost the report somewhere between browser tabs. One moment it was there in the Gemini app, a detailed deep research analysis on how AI agents communicate with each other, complete with citations and a synthesis I’d spent an hour reviewing. The next moment, gone. Along with the draft blog post I’d been weaving it into.

I was working on part nine of my Agentic Shift series, trying to answer the question of what happens when agents start talking to each other instead of just talking to us. The research was sprawling—academic papers on multi-agent systems, documentation from LangGraph and AutoGen, blog posts from researchers at DeepMind and OpenAI. I’d been using Gemini’s deep research feature in the app to help synthesize all of this, and it was genuinely useful. The AI would spend minutes thinking through the question, querying sources, building a structured report. But then I had to move that report into my text-based workflow. Copy, paste, reformat, lose formatting, copy again. Somewhere in that dance between the browser and my terminal, I lost everything.

I stared at the empty browser tab for a moment. I could start over, rerun the research in the Gemini app, be more careful about saving this time. But this wasn’t the first time I’d hit this friction. Every time I used deep research in the browser, I had to bridge two worlds: the app where the AI did its thinking, and the terminal where I actually write and build.

What looked like yak shaving was actually a prerequisite. I needed deep research capabilities in my terminal workflow, not just wanted them. I couldn’t keep jumping between environments. And I was in luck. Just a few weeks earlier, Google had announced that deep research was now available through the Gemini API. The capability I’d been using in the browser could be accessed programmatically.

When Features Live in the Wrong Place

I’m not going to pretend this was built based on demand from the community. I needed this. Specifically, I needed to stop context-switching between the Gemini app and my terminal, because every time I did, I was introducing friction and risk. The lost report was just the most recent symptom of a workflow that was fundamentally broken for how I work.

I live in the terminal. My notes are markdown files. My drafts are plain text. My build process, my git workflow, my entire development environment assumes I’m working with files and command-line tools. When I have to move work from a browser back into that environment, I’m not just inconvenienced—I’m fighting against the grain of everything else I do.

Deep research is powerful. It works. But living in a web app meant it was disconnected from the places where I actually needed it. Sure, other people might benefit from having this integrated into MCP-compatible tools, but that’s a nice side effect. The real reason I built this was simpler: I had to finish part nine of the Agentic Shift series, and I couldn’t do that without fixing my workflow first.

The Model Context Protocol made this possible. It’s a standard for exposing AI capabilities as tools that can plug into different environments. Google’s API gave me the primitives. I just needed to connect them to where I actually work.

Building the Missing Piece

The extension wraps Gemini’s deep research capabilities into the Model Context Protocol, which means it integrates seamlessly with Gemini CLI and any other MCP-compatible client. The architecture is deliberately simple, but it supports two distinct workflows depending on what you need.

The first workflow is straightforward: you have a research question, and you want a deep investigation. You can kick off research with a simple command, but if you use the bundled /deep-research:start slash command, the model actually guides you through a step to optimize your question to get the most out of deep research. The agent then spends tens of minutes—or as much time as it needs—planning the investigation, querying sources, and synthesizing findings into a detailed report with citations you can follow up on.

The second workflow is for when you want to ground the research in your own documents. You use /deep-research:store-create to set up a file search store, then /deep-research:store-upload to index your files. Once they’re uploaded, you have two options: you can include that dataset in the deep research process so the agent grounds its investigation in your specific sources, or you can query against it directly for a simpler RAG experience. This is the same File Search capability I wrote about in November when I rebuilt my Podcast RAG system, but now it’s accessible from the terminal as part of my normal workflow.

The extension maintains local state in a workspace cache, so you don’t have to remember arcane resource identifiers or lose track of running research jobs. The whole thing is designed to feel as natural as running a grep command or kicking off a build—it’s just another tool in the environment where I already work.

So did it actually work?

The first time I ran it, I asked for a deep dive into Stonehenge construction. I’d been reading Ken Follett’s novel Circle of Days and found myself curious about the scientific evidence behind the story, what do we actually know about how it was built and who built it. I kicked off the query and watched something fascinating happen. The model understood that deep research takes time. Instead of just waiting silently, it kept checking in to see if the research was done, almost like checking the oven to see if dinner was ready. Twenty minutes later, a markdown file appeared in my filesystem with a comprehensive research report, complete with citations to academic sources, isotope analysis, and archaeological evidence. I didn’t have to copy anything from a browser. I didn’t lose any formatting. It was just there, ready to reference. The report mentioned the Bell Beaker culture and what happened to the Neolithic builders around 2500 BCE, which sent me down another rabbit hole. I immediately ran a second research query on that transition. Same seamless experience. That’s when I knew this was exactly what I needed.

What This Actually Means

I think extensions like this represent something important about where AI development is heading. We’re past the proof-of-concept phase where every AI interaction is a magic trick. Now we’re in the phase where AI capabilities need to integrate into actual workflows—not replace them, but augment them in ways that feel natural.

This is what I wrote about in November when I talked about the era of Personal Software. We’ve crossed a threshold where building a bespoke tool is often faster—and certainly less frustrating—than trying to adapt your workflow to someone else’s software. I didn’t build this extension for the community. I built it because I needed it. I had lost work, and I needed to stop context-switching between environments. If other people find it useful, that’s a nice side effect, but it’s fundamentally software for an audience of one.

The key insight for me was that the Model Context Protocol isn’t just a technical standard; it’s a design pattern for making AI tools composable. Instead of building a monolithic research application with its own UI and workflow, I built a small, focused extension that does one thing well and plugs into the environment where I already work. That composability matters because it means the tool can evolve with my workflow rather than forcing my workflow to evolve around the tool.

There’s also something interesting happening with how we think about AI capabilities. Deep research isn’t about making the model smarter—it’s about giving it time and structure. The same model that gives you a superficial answer in three seconds can give you a genuinely insightful report if you let it think for tens of minutes and provide it with the right sources. We’re learning that intelligence isn’t just about raw capability; it’s about how you orchestrate that capability over time.

What Comes Next

The extension is live on GitHub now, and I’m using it daily for my own research workflows. The immediate next step is adding better control over the research format—right now you can specify broad categories like “Technical Deep Dive” or “Executive Brief,” but I want more granular control over structure and depth. I’m also curious about chaining multiple research tasks together, where the output of one investigation becomes the input for the next.

But the bigger question I’m sitting with is what other AI capabilities are hiding in plain sight, waiting for someone to make them accessible. Deep research was always there in the Gemini API; it just needed a wrapper that made it feel like a natural part of the development workflow. What else is out there?

If you want to try it yourself, you’ll need a Gemini API key (get one at ai.dev) and set the GEMINI_DEEP_RESEARCH_API_KEY environment variable. Deep research runs on Gemini 3.0 Pro, and you can find the current pricing here. It’s charged based on token consumption for the research process plus any tool usage fees.

Install the extension with:

gemini extensions install https://github.com/allenhutchison/gemini-cli-deep-research --auto-update

The full source is on github.

As for me, I still need to finish part nine of the Agentic Shift series. But now I can get back to it with the confidence that I’m working in my preferred environment, with the tools I need accessible right from the terminal. Fair warning: once you start using AI for actual deep research, it’s hard to go back to the shallow stuff.

A retro computer monitor displaying the Gemini CLI prompt "> Ask Gemini to scaffold a web app" inside a glowing neon blue and pink holographic wireframe box, representing a digital sandbox.

The Guardrails of Autonomy

Allen Hutchison3 Comments

I still remember the first time I let an LLM execute a shell command on my machine. It was a simple ls -la, but my finger hovered over the Enter key for a solid ten seconds.

There is a visceral, lizard-brain reaction to giving an AI that level of access. We all know the horror stories—or at least the potential horror stories. One hallucinated argument, one misplaced flag, and a helpful cleanup script becomes rm -rf /. This fear creates a central tension in what I call the Agentic Shift. We want agents to be autonomous enough to be useful—fixing a bug across ten files while we grab coffee—but safe enough to be trusted with the keys to the kingdom.

Until now, my approach with the Gemini CLI was the blunt instrument of “Human-in-the-Loop.” Any tool call with a side effect—executing shell commands, writing code, or editing files—required a manual y/n confirmation. It was safe, sure. But it was also exhausting.

I vividly remember asking Gemini to “fix all the linting errors in this project.” It brilliantly identified the issues and proposed edits for twenty different files. Then I sat there, hitting y… y… y… twenty times.

The magic evaporated. I wasn’t collaborating with an intelligent agent; I was acting as a slow, biological barrier for a very expensive macro. This feeling has a name—“Confirmation Fatigue”—and it’s the silent killer of autonomy. I realized I needed to move from micromanagement to strategic oversight. I didn’t want to stop the agent; I wanted to give it a leash.

The Policy Engine

The solution I’ve built is the Gemini CLI Policy Engine.

Think of it as a firewall for tool calls. It sits between the LLM’s request and your operating system’s execution. Every time the model reaches for a tool—whether it’s to read a file, run a grep command, or make a network request—the Policy Engine intercepts the call and evaluates it against a set of rules.

The system relies on three core actions:

  1. allow: The tool runs immediately.
  2. deny: The AI gets a “Permission denied” error.
  3. ask_user: The default manual approval.

A Hierarchy of Trust

The magic isn’t just in blocking or allowing things; it’s in the hierarchy. Instead of a flat list of rules, I built a tiered priority system that functions like layers of defense.

At the base, you have the Default Safety Net. These are the built-in rules that apply to everyone—basic common sense like “always ask before overwriting a file.”

Above that sits the User Layer, which is where I define my personal comfort zone. This allows me to customize the “personality” of my safety rails. On my personal laptop, I might be a cowboy, allowing git commands to run freely because I know I can always undo a bad commit. But on a production server, I might lock things down tighter than a vault.

Finally, at the top, is the Enterprise/Admin Layer. These are the immutable laws of physics for the agent. In an enterprise setting, this is where you ensure that no matter how “creative” the agent gets, it can never curl data to an external IP or access sensitive directories.

Safe Exploration

In practice, this means I can trust the agent to look but ask it to verify before it touches. I generally trust the agent to check the repository status, review history, or check if the build passed. I don’t need to approve every git log or gh run list.

[[rule]]
toolName = "run_shell_command"
commandPrefix = [
  "git status",
  "git log",
  "git diff",
  "gh issue list",
  "gh pr list",
  "gh pr view",
  "gh run list"
]
decision = "allow"
priority = 100

Yolo Mode

Sometimes, I’m working in a sandbox and I just want speed. I can use the dedicated yolo mode to take the training wheels off. There is a distinct feeling of freedom—and a slight thrill of danger—when you watch the terminal fly by, commands executing one after another.

However, even in Yolo mode, I want a final sanity check before I push code or open a PR. While Yolo mode is inherently permissive, I define specific high-priority rules to catch critical actions. I also explicitly block docker commands—I don’t want the agent spinning up (or spinning down) containers in the background without me knowing.

# Exception: Always ask before committing or creating a PR
[[rule]]
toolName = "run_shell_command"
commandPrefix = ["git commit", "gh pr create"]
decision = "ask_user"
priority = 900
modes = ["yolo"]

# Exception: Never run docker commands automatically
[[rule]]
toolName = "run_shell_command"
commandPrefix = "docker"
decision = "deny"
priority = 999
modes = ["yolo"]

The Hard Stop

And then there are the things that should simply never happen. I don’t care how confident the model is; I don’t want it rebooting my machine. These rules are the “break glass in case of emergency” protections that let me sleep at night.

[[rule]]
toolName = "run_shell_command"
commandRegex = "^(shutdown|reboot|kill)"
decision = "deny"
priority = 999

Decoupling Capability from Control

The significance of this feature goes beyond just saving me from pressing y. It fundamentally changes how we design agents.

I touched on this concept in my series on autonomous agents, specifically in Building Secure Autonomous Agents, where I argued that a “policy engine” is essential for scaling from one agent to a fleet. Now, I’m bringing that same architecture to the local CLI.

Previously, the conversation around AI safety often presented a binary choice: you could have a capable agent that was potentially dangerous, or a safe agent that was effectively useless. If I wanted to ensure the agent wouldn’t accidentally delete my home directory, the standard advice was to simply remove the shell tool. But that is a false choice. It confuses the tool with the intent. Removing the shell doesn’t just stop the agent from doing damage; it stops it from running tests, managing git, or installing packages—the very things I need it to do.

With the Policy Engine, I can give the agent powerful tools but wrap them in strict policies. I can give it access to kubectl, but only for get commands. I can let it edit files, but only on specific documentation sites.

This is how we bridge the gap between a fun demo and a production-ready tool. It allows me to define the sandbox in which the AI plays, giving me the confidence to let it run autonomously within those boundaries.

Defining Your Own Rules

The Policy Engine is available now in the latest release of Gemini CLI. You can dive into the full documentation here.

If you want to see exactly what rules are currently active on your system—including the built-in defaults and your custom additions—you can simply run /policies list from inside the Gemini CLI.

I’m currently running a mix of “Safe Exploration” and “Hard Stop” rules. It’s quieted the noise significantly while keeping my file system intact. I’d love to hear how you configure yours—are you a “deny everything” security maximalist, or are you running in full “allow” mode?

A stylized, dark digital illustration of an open laptop displaying lines of blue code. Floating above the laptop are three glowing, neon blue wireframe icons: a document on the left, a calendar in the center, and an envelope on the right. The icons appear to be formed from streams of digital particles rising from the laptop screen, symbolizing the integration of digital tools. The overall aesthetic is futuristic and high-tech, with dramatic lighting emphasizing the connection between the code and the applications.

Bringing the Office to the Terminal

Allen Hutchison3 Comments

There is a specific kind of friction that every developer knows. It’s the friction of the “Alt-Tab.”

You’re deep in the code, holding a complex mental model of a system in your head, when you realize you need to check a requirement. That requirement lives in a Google Doc. Or maybe you need to see if you have time to finish a feature before your next meeting. That information lives in Google Calendar.

So you leave the terminal. You open the browser. You navigate the tabs. You find the info. And in those thirty seconds, the mental model you were holding starts to evaporate. The flow is broken.

But it’s not just the context switch that kills your momentum—it’s the ambush. The moment you open that browser window, the red dots appear. Chat pings, new emails, unresolved comments on a doc you haven’t looked at in two days—they all clamor for your attention. Before you know it, the quick thing you needed to look up has morphed into an hour of answering questions and putting out fires. You didn’t just lose your place in the code; you lost your afternoon.

I’ve been thinking a lot about this friction lately, especially as I’ve moved more of my workflow into the Gemini CLI. If we want AI to be a true partner in our development process, it can’t just live in a silo. It needs access to the context of our work—and for most of us, that context is locked away in the cloud, in documents, chats, and calendars.

That’s why I built the Google Workspace extension for Gemini CLI.

Giving the Agent “Senses“

We often talk about AI agents in the abstract, but their utility is defined by their boundaries. An agent that can only see your code is a great coding partner. An agent that can see your code and your design documents and your team’s chat history? That’s a teammate.

This extension connects the Gemini CLI to the Google Workspace APIs, effectively giving your terminal-based AI a set of digital senses and hands. It’s not just about reading data; it’s about integrating that data into your active workflow.

Here is what that looks like in practice:

1. Contextual Coding

Instead of copying and pasting requirements from a browser window, you can now ask Gemini to pull the context directly.

“Find the ‘Project Atlas Design Doc’ in Drive, read the section on API authentication, and help me scaffold the middleware based on those specs.”

2. Managing the Day

I often get lost in work and lose track of time. Now, I can simply ask my terminal:

“Check my calendar for the rest of the day. Do I have any blocks of free time longer than two hours to focus on this migration?”

3. Seamless Communication

Sometimes you just need to drop a quick note without leaving your environment.

“Send a message to the ‘Core Eng’ chat space letting them know the deployment is starting now.”

The Accidental Product

Truth be told, I didn’t set out to build a product. When I first joined Google DeepMind, this was simply my “starter project.” My manager suggested I spend a few weeks experimenting with Google Workspace and our agentic capabilities, and the Gemini CLI seemed like the perfect sandbox for that kind of exploration.

I started building purely for myself, guided by my own daily friction. I wanted to see if I could check my calendar without leaving the terminal. Then I wanted to see if I could pull specs from a Doc. I followed the path of my own curiosity, adding tools one by one.

But when I shared this little experiment with a few colleagues, the reaction was immediate. They didn’t just think it was cool; they wanted to install it. That’s when I realized this wasn’t just a personal hack—it was a shared need. It snowballed from a few scripts into a full-fledged extension that we knew we had to ship.

Under the Hood

The extension is built as a Model Context Protocol (MCP) server, which means it runs locally on your machine. It uses your own OAuth credentials, so your data never passes through a third-party server. It’s direct communication between your local CLI and the Google APIs.

It currently supports a wide range of tools across the Workspace suite:

  • Docs & Drive: Search for files, read content, and even create new docs from markdown.
  • Calendar: List events, find free time, and schedule meetings.
  • Gmail: Search threads, read emails, and draft replies.
  • Chat: Send messages and list spaces.

Why This Matters

This goes back to the idea of “Small Tools, Big Ideas.” Individually, a command-line tool to read a calendar isn’t revolutionary. But when you combine that capability with the reasoning engine of a large language model, it becomes something else entirely.

It turns your terminal into a cockpit for your entire digital work life. It allows you to script interactions between your code and your company’s knowledge base. It reduces the friction of context switching, letting you stay where you are most productive.

If you want to try it out, the extension is open source and available now. You can install it directly into the Gemini CLI:

gemini extensions install https://github.com/gemini-cli-extensions/workspace

I’m curious to see how you all use this. Does it change your workflow? Does it keep you in the flow longer? Give it a spin and let me know.

Abstract digital visualization of glowing lines and nodes converging on a central geometric shape labeled 'AGENTS.md', symbolizing interconnected AI systems and a unifying standard.

On Context, Agents, and a Path to a Standard

Allen HutchisonLeave a comment

When we were first designing the Gemini CLI, one of the foundational ideas was the importance of context. For an AI to be a true partner in a software project, it can’t just be a stateless chatbot; it needs a “worldview” of the codebase it’s operating in. It needs to understand the project’s goals, its constraints, and its key files. This philosophy isn’t unique; many agentic tools use similar mechanisms. In our case, it led to the GEMINI.md context system (which was first introduced in this commit) a simple Markdown file that acts as a charter, guiding the AI’s behavior within a specific repository.

At its core, GEMINI.md is designed for clarity and flexibility. It gives developers a straightforward way to provide durable instructions and file context to the model. We also recognized that not every project is the same, so we made the system adaptable. For instance, if you prefer a different convention, you can easily change the name of your context file with a simple setting.

This approach has worked well, but I’ve always been mindful that bespoke solutions, however effective, can lead to fragmentation. In the open, collaborative world of software development, standards are the bridges that connect disparate tools into a cohesive ecosystem.

That’s why I’ve been following the emergence of the Agents.md specification with great interest. We have several open issues in the Gemini CLI repo (like #406 and #12345) from users asking for Agents.md support, so there’s clear community interest. The idea of a universal standard for defining an AI’s context is incredibly appealing. A shared format would mean that a context file written for one tool could work seamlessly in another, allowing developers to move between tools without friction. I would love for Gemini CLI to become a first-class citizen in that ecosystem.

However, as I’ve considered a full integration, I’ve run into a few hurdles—not just technical limitations, but patterns of use that a standard would need to address. This has led me to a more concrete set of proposals for what an effective standard would need.

So, what would it take to bridge this gap? I believe with a few key additions, Agents.md could become the robust standard we need. Here’s a more detailed breakdown of what I believe is required:

  1. A Standard for @file Includes: From my perspective, this is mandatory. In any large project, you need the ability to break down a monolithic context file into smaller, logical, and more manageable parts—much like a C/C++ #include. A simple @file directive, which GEMINI.md and some other systems support, would provide the modularity needed for real-world use.
  2. A Pragma System for Model-Specific Instructions: Developers will always want to optimize prompts for specific models. To accommodate this without sacrificing portability, the standard could introduce a pragma system. This could leverage standard Markdown callouts to tag instructions that only certain models should pay attention to, while others ignore them. For example:

    > [!gemini]
    > Gemini only instructions here

    > [!claude]
    > Claude only instructions here

    > [!codex]
    > Codex only instructions here
  3. Clear Direction on Context Hierarchy: We need clear rules for how an agentic application should discover and apply context. Based on my own work, I’d propose a hierarchical strategy. When an agent is invoked, it should read the context in its current directory and all parent directories. Then, when it’s asked to read a specific file, it should first apply the context from that file’s local directory before applying the broader, inherited context. This ensures that the most specific instructions are always considered first, creating a predictable and powerful system.

If the Agents.md standard were to incorporate these three features, I believe it would unlock a new level of interoperability for AI developer tools. It would create a truly portable and powerful way to define AI context, and I would be thrilled to move Gemini CLI to a model of first-class support.

The future of AI-assisted development is collaborative, and shared standards are the bedrock of that collaboration. I’ve begun outreach to the Agents.md maintainers to discuss these proposals, and I’m optimistic that with community feedback, we can get there. If you have your own opinions on this, I’d love to hear them in the discussion on our repo.

Unlocking the Future of Coding: Introducing the Gemini CLI

Allen Hutchison2 Comments

Back in April, I wrote about waiting for the true AI coding partner. I articulated a vision for an AI that transcends mere code generation, one that truly understands context, acts autonomously within our development environments, and collaborates with us iteratively. Today, I’m thrilled to announce a significant step towards that vision: the launch of the Gemini CLI.

For too long, AI coding assistance has often felt like a disconnected assistant. While dedicated AI-powered IDEs like Cursor have made great strides, the common experience still involves copy-pasting code into a separate interface or breaking flow to get suggestions. This breaks flow, loses context, and frankly, isn’t how truly collaborative partners work. We need an AI that lives where we live—in the terminal, within our projects, and deeply integrated into our workflow.

This is precisely what the Gemini CLI sets out to achieve. It’s not just a fancy chatbot for your command line; it’s an experimental interface designed to bring the power of Gemini directly into your development loop, enabling intelligent, contextual, and actionable AI assistance.

It’s for this very reason that I’ve been quite heads-down over the last few months, working with a super talented team to bring this application to life. It has genuinely been one of my most fun experiences at Google in the 20+ years that I’ve been here, and I feel incredibly fortunate to have had the chance to collaborate with such brilliant people across the company.

The Power of Small Tools, Amplified by AI

In May, I explored the concept of small tools, big ideas. The premise was simple: complex problems are often best tackled by composing many small, powerful, and specialized tools. This philosophy is at the very heart of the Gemini CLI’s design.

Instead of a monolithic AI trying to do everything at once, the Gemini CLI empowers Gemini with a suite of familiar command-line tools. Imagine an AI that can:

  • Read and Write Files: Using read_file and write_file, it can inspect your codebase, understand existing logic, and propose modifications directly to your files.
  • Navigate Your Project: With list_directory and grep, it can explore your project structure, locate relevant files, or find specific patterns across your repository, just like you would.
  • Execute Shell Commands: The run_shell_command tool allows Gemini to execute commands, build your project, run tests, or even interact with external services, providing real-time feedback.
  • Search the Web: Need to look up an API, debug an error message, or find best practices? The google_web_search tool lets Gemini leverage the vastness of the internet to inform its responses and actions.
  • Edit with Precision: Beyond simple file writes, the edit_file tool allows for granular, diff-based modifications, ensuring changes are precise and reviewable.

This approach means Gemini isn’t guessing; it’s acting. It’s using the same building blocks you use every day, but with its powerful reasoning capabilities to orchestrate them towards your goals.

A Truly Contextual and Collaborative Partner

The Gemini CLI maintains a persistent session, remembering your conversation history, the files it has examined, and the results of previous tool executions. This “conversational memory” and contextual understanding are critical. It allows for a natural, iterative back-and-forth, where the AI builds on prior interactions and its understanding of your project state.

You can ask Gemini to:

  • “Find all JavaScript files in this directory that import React.” (Leveraging list_directory and grep)
  • “Refactor this component to use hooks.” (Involving read_file, edit_file, and potentially run_shell_command to run tests).
  • “What’s the best way to implement X in Python given these files?” (Using read_file to understand your existing code and google_web_search for best practices).

The workflow is truly interactive. Gemini proposes actions, and you have the power to approve them or guide it further. This human-in-the-loop design ensures you’re always in control, fostering a collaborative partnership rather than a black-box operation.

Built by Gemini CLI, For Everyone

It’s particularly exciting to share that this project was started by a small and scrappy team, and we leveraged Gemini CLI itself to help write Gemini CLI. Many of us now work almost exclusively within Gemini CLI, often using our IDEs only for viewing diffs.

And while its origins are in coding, Gemini CLI is incredibly versatile for many tasks outside of traditional development. Personally, I love using it to manage my home lab, to bulk rename and reformat files for my podcast project, and to generally act as a seamless go-between for anything complicated in GitHub. Increasingly, I’ve also been using Gemini CLI with Obsidian to understand and extract insights from my vault. With over 9000 files in my work vault alone, Gemini CLI lets me ask questions of the entire vault and even make large refactoring-style changes across the entire thing.

Beyond Today: Extensibility

One of the most exciting aspects of the Gemini CLI, and a direct nod to the “small tools, big ideas” philosophy, is its extensibility. The underlying architecture allows developers to define custom tools. This means you can teach Gemini to interact with your specific internal systems, proprietary APIs, or niche development tools. The possibilities are endless, transforming Gemini into an AI assistant perfectly tailored to your unique development environment.

Get Started Today

The Gemini CLI represents a significant leap forward in bringing intelligent AI assistance directly to where developers work most effectively: the command line. It’s a practical realization of the “true AI coding partner” vision, built on the principle that small, well-designed tools can achieve big ideas when orchestrated by a powerful intelligence.

Ready to try it out? Head over to the Gemini CLI GitHub repository to get started. Explore the commands, experiment with its capabilities, and let’s shape the future of AI-powered development together.

I’m incredibly excited about what this means for developer productivity and the evolving role of AI in our daily coding lives. Let me know what you build with it!