What AI models does the agent use?

The agent has access to Claude, DeepSeek, Gemini, and other top models. It automatically routes to the best model for each task — you never have to think about API keys or token limits.

Yes. Each agent runs in an isolated environment. We don't train on your data, and you can export or delete everything at any time. The underlying engine (GoGogot) is open-source, so you can audit exactly how it works.

What can the agent actually do?

Browse the web, process files (CSV, PDF, images), run scheduled tasks, remember context across sessions, and communicate via Telegram or Slack. Think of it as a capable junior employee, not a chatbot.

How does memory work?

The agent maintains persistent memory across sessions. It remembers your preferences, past conversations, and task context. You can also explicitly tell it to remember or forget things.

Can I self-host the agent?

Absolutely. GoGogot is 100% open-source. Run it on your own hardware for free. cowork.ink is the managed version — we handle servers, model costs, updates, and uptime so you don't have to.

Is there a free trial?

We offer a 7-day money-back guarantee. Spin up an agent, give it real tasks, and if it doesn't save you time, we'll refund you — no questions asked.

What is the difference between a persistent and an ephemeral AI agent?

A persistent AI agent stores memory across sessions — it remembers past interactions, learns user preferences, and builds context over time. An ephemeral agent starts fresh every session with no memory of previous interactions. Persistent agents improve with use; ephemeral agents are stateless by design.

When should you use an ephemeral AI agent?

Use ephemeral agents for tasks where privacy and predictability matter most: processing sensitive documents, one-off analytical tasks, compliance-sensitive workflows, or any scenario where carrying forward context is a liability rather than an asset. Ephemeral agents are also easier to scale and test consistently.

Why are persistent AI agents better for personal assistants?

Personal AI assistants need to remember who you are, what you care about, and what you've already discussed. An ephemeral assistant asks for your dietary restrictions every single meal. A persistent assistant remembers you're vegetarian, you avoid dairy, and you dislike cilantro — and improves its recommendations accordingly. See [AI agent memory](/blog/ai-agent-memory/) for how this is implemented.

How do persistent AI agents store memory?

Persistent agents use external storage layers: vector databases (Pinecone, Weaviate, Chroma) for semantic search over past experiences, key-value stores (Redis) for fast structured fact lookup, and relational databases for structured interaction history. Frameworks like Mem0, Zep, and LangMem manage this automatically.

Are persistent AI agents a security risk?

They can be if not designed carefully. Memory is an attack surface — prompt injection attacks can plant false memories, and accumulated data can leak sensitive information. Best practice is to scope memory tightly (store insights, not raw conversations), use access controls, and audit what's stored. Read our [AI agent security guide](/blog/ai-agent-security/) for a full treatment.

Persistent vs. Ephemeral AI Agents: Why Memory Makes Agents 4x Better

Persistent AI agents remember everything. Ephemeral agents start fresh. Which type to build, when memory matters & the real performance gap.

Frequently Asked Questions

What is the difference between a persistent and an ephemeral AI agent?: A persistent AI agent stores memory across sessions — it remembers past interactions, learns user preferences, and builds context over time. An ephemeral agent starts fresh every session with no memory of previous interactions. Persistent agents improve with use; ephemeral agents are stateless by design.
When should you use an ephemeral AI agent?: Use ephemeral agents for tasks where privacy and predictability matter most: processing sensitive documents, one-off analytical tasks, compliance-sensitive workflows, or any scenario where carrying forward context is a liability rather than an asset. Ephemeral agents are also easier to scale and test consistently.
Why are persistent AI agents better for personal assistants?: Personal AI assistants need to remember who you are, what you care about, and what you've already discussed. An ephemeral assistant asks for your dietary restrictions every single meal. A persistent assistant remembers you're vegetarian, you avoid dairy, and you dislike cilantro — and improves its recommendations accordingly. See [AI agent memory](/blog/ai-agent-memory/) for how this is implemented.
How do persistent AI agents store memory?: Persistent agents use external storage layers: vector databases (Pinecone, Weaviate, Chroma) for semantic search over past experiences, key-value stores (Redis) for fast structured fact lookup, and relational databases for structured interaction history. Frameworks like Mem0, Zep, and LangMem manage this automatically.
Are persistent AI agents a security risk?: They can be if not designed carefully. Memory is an attack surface — prompt injection attacks can plant false memories, and accumulated data can leak sensitive information. Best practice is to scope memory tightly (store insights, not raw conversations), use access controls, and audit what's stored. Read our [AI agent security guide](/blog/ai-agent-security/) for a full treatment.