When Gavriel Cohen encountered OpenClaw, he was immediately drawn to the tool. At that moment, Cohen—who would go on to establish NanoClaw and NanoCo AI—had stepped away from development work to focus on marketing initiatives.
Cohen recounts to The New Stack that he was actively working with Anthropic's Claude Code, which rekindled his passion for programming, when he discovered what was then called Clawd Bot, OpenClaw's predecessor. "I had my first little go," he explains. "I installed it, connected it to my WhatsApp, sent a few messages back and forth. So I came to it really from a need as we were building an AI native marketing agency."
Before this experience, Claude Code itself—featuring a terminal-driven LLM interface—had sparked his interest in returning to development. "I immediately tried it, and that was a big mental unlock, so around March of 2025 I knew I needed to start building again." Previously, Cohen had worked as a developer at Wix, the no-code website platform headquartered in Tel Aviv.
Cohen recognized something missing from his workflow. "I was mapping out what I needed, and I actually bought a Mac mini just to run Claude Code in the background and set up scheduled recurring jobs." His initial engagement with OpenClaw seemed promising.
Discovering His Own Code in the Project
The problems surfaced remarkably fast. "It was pretty immediate," Cohen recalls. "I was going through the setup that gives you all these options for different packages to install — and one of them was a package that I had built a few months before called NanoPDF. I saw that and thought, 'Why did they include that tiny package?'"
Most developers would expect to see only well-established, thoroughly vetted third-party packages in such a setup. Cohen's package was neither—it carried minimal stars and hadn't received updates in months. Yet this was just the beginning of his concerns.
"Then in the first day or two I was debugging, after a scheduled job didn't fire, and I saw the logs of all the WhatsApp messages — not just the one group that I connected it to, but all of them."
The Unmaintainable Codebase Problem
Careless development practices combined with security oversights represent serious warning signs for any developer. Cohen emphasizes this observation repeatedly during his conversation with The New Stack, and for good reason: while policies can be adjusted and coding standards tightened, a codebase that balloons into an unmanageable state becomes essentially unsalvageable. Even open source initiatives face limits on how many contributors can meaningfully review code. By February, OpenClaw had accumulated more than 3,000 unresolved pull requests.
"But most importantly, I looked at the code base, and it's like a half a million lines of code."
Cohen's marketing operation employed just three people. "We had customers, so I wanted to have an agent for each customer, but I couldn't connect this thing to my customer data, and I couldn't build a business on top of it," he says.
Cohen took the only path forward he could see. "I sat down to build NanoClaw. I had to make this super small because in order for anybody who cares about security to use it, they're going to have to be able to look over the code and actually see what's going on and be OK with it."
Understanding the Architecture
A natural question emerges: what comprises OpenClaw from an architectural perspective?
"So at the core," Cohen explains, "you have a coding agent. It can write code and run Bash commands, so you need a persistent environment session. And then you have to connect to a messaging app. And then the fourth thing is connection to the internet."
He continues: "From those 4 fundamental capabilities you can build out everything else. And it is proactive because once you start scheduling jobs, it's no longer just reacting to what you're saying. You can write a claw agent in as little as 25 lines."
Despite OpenClaw's obvious shortcomings, Cohen remains firm in his assessment of the core issue. "I think it was fundamentally flawed from the beginning, and the fatal flaw is half a million lines of code." (Current data shows OpenClaw now contains over 800,000 lines of code). Following OpenAI's acquisition of OpenClaw, usability challenges persisted, and community engagement has declined significantly.
Has NanoClaw simplified the setup process? Cohen paused before responding. "I still think of NanoClaw, for the most part, as suited to technical people — not necessarily developers, but those comfortable with the terminal and GitHub. NanoClaw is not shipped as a binary. Everybody runs it from source."
The current iteration includes a terminal-based setup script that guides users through each step. Installation issues are routed to Claude for resolution. Cohen expresses reservations about this approach; involving Claude introduces security considerations. "If you don't understand the security model and you're just running Claude, it can break the security model or remove the sandboxing."
Why Containers Became Central
What drove NanoClaw's decision to employ containers, and has this choice created a market advantage?
"When I actually sat down to write NanoClaw, I just started from an empty project, and I didn't tell Claude Code to go look at OpenClaw," Cohen responds. "I just described the capabilities. I said I want a messaging app; a coding agent; I want it in a loop and I want memory and I built it from scratch."
As Cohen began development, new challenges emerged. "I thought: which tools should I give it? I don't want it to be limited and unable to run bash commands, but if I want to let it run any command, it's got to be in an isolated environment. I can't just have it running on my machine with an autonomous agent able to do everything, so I put it in an isolated container." This containerization approach gave NanoClaw a distinctive competitive edge.
One detail stands out: "We started with Apple containers."
"I was running it on a Mac mini, and I was vaguely aware that Apple had added this new native container capability. That worked really well initially, but when thousands of people started using it, everybody wondered, 'What are you doing with Apple containers? Docker is the default; it's a standard that works everywhere.' So I supported both and then within a few weeks I just changed the default to Docker containers."
NanoClaw formed a partnership with OneCLI to leverage their credential management and proxying infrastructure for enhanced security. However, this introduces a conceptual shift. "The user base and the community gets it," Cohen notes. "Before we had that partnership, there was a major issue with credentials entering the agent environment that we were trying to prevent — but, for example, you need to get the Anthropic token in place so that the agent can connect."
Initially, NanoClaw developed their own proxying mechanism, but complexity grew. "OneCLI was a very natural partnership, and the user base was happy to have a proper solution. We also have human-in-the-loop approvals, and set policies around — for example — how your agent can use Gmail."
Strategic Partnerships and Future Direction
Vercel frequently appears in discussions about NanoClaw. What does the actual integration entail, and where does it rank on the development roadmap?
"Vercel created this great open-source package called Chat SDK, which gives you standardized connections to about 15 or 20 different messaging apps. One of the core philosophies I came to NanoClaw with is don't reinvent the wheel. Why should everybody be re-implementing the same integrations with messaging apps — let's have one library that we all congregate around."
OpenClaw has established itself as a distinct software category. What must NanoClaw accomplish over the coming year to not merely assume the role, but reshape the category?
"What we've been doing with credential proxies, human-in-the-loop approvals, and building with isolation of agents is tackling head-on the big hairy problems and challenges that stand between using autonomous agents with their full power, while doing it in a way that's safe."
Enterprise Focus Ahead
"In the next few months, we are looking at large business enterprises that have strict security requirements, compliance requirements, regulatory requirements, etc. So we've already gotten to the point where we have the offering where you can connect to your email, you can connect to your calendar and do that safely where any sensitive action has approval."
Breaking into the enterprise segment presents inherent difficulties for smaller operations. Yet NanoClaw has a clear vision of its target market, positioning it as a potential contender to inherit OpenClaw's abandoned leadership position as competitors vie for dominance.
Source: The New Stack