# Agent Zero Open work agent with a Linux environment for browsers, files, code and documents. Canonical profile: https://ki-agentenkompass.de/en/agents/agent-zero/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-10-12 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview The A0 Launcher simplifies Agent Zero setup and is an entry point to the same product. - Provider: Agent Zero, s.r.o. - Product family: Agent Zero - Profile type: Self-hosted work agent - Environment: Docker on your computer or server - Connections: Browser, terminal, files, MCP and plugins - Setup: Install Docker, start an instance and configure a cloud or local model. - Pricing model: MIT-licensed; model and hosting costs are additional. ## Key features ### Dedicated Linux environment Agents work with terminals, files and desktop tools inside a Docker environment. Source: https://www.agent-zero.ai/p/docs/ ### Control a browser Browser tools enable interaction with websites. Source: https://www.agent-zero.ai/p/docs/ ### Separate projects Projects group files, instructions and context for separate areas of work. Source: https://www.agent-zero.ai/p/docs/ ### Delegate subtasks Agent Zero can distribute tasks to specialized subagents. Source: https://www.agent-zero.ai/p/docs/ ### Extend tools Plugins, skills and MCP connect additional capabilities and services. Source: https://www.agent-zero.ai/p/docs/ ## Example workflows ### Process documents - Your input: Shared files and a clear task. - Possible result: A structured overview of the supplied documents. - What to check: Check statements, files and granted access. ### Delegate research - Your input: A topic and a bounded set of sources. - Possible result: A research draft with traceable sources. - What to check: Open sources and review conclusions. ## Requirements and limits ### Set up hosting Requirement: Docker and configured model access are required. Source: https://www.agent-zero.ai/p/docs/installation/ ### Set file access Requirement: Configure host access and shared directories deliberately. Source: https://www.agent-zero.ai/p/docs/ ### Reliability in your workflow Not yet confirmed: Information is based on provider sources; success rates for specific workflows have not been measured here. Source: https://www.agent-zero.ai/p/docs/ ## A good fit if … - you can run Docker on your own machine or server and manage the instance yourself - you want the agent to work in a Linux workspace with a browser and files - you want to schedule tasks via cron or at fixed times ## Less suitable if … - you want a hosted product without installation and updates - you need management with roles and administrator approvals; the reviewed pages describe none Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Open choice You set a main and a utility model yourself: with your own key, OpenRouter, an account sign-in such as ChatGPT, or an OpenAI-compatible endpoint. Models run locally through Ollama, LM Studio, llama.cpp, oMLX or vLLM. Plugins add further providers. - Model families named: OpenAI (GPT), Anthropic (Claude), Google (Gemini), xAI (Grok), DeepSeek, Mistral, Moonshot (Kimi), Z.ai (GLM) · Other models can be connected freely - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: Yes - Local models: Yes Documented · Sources accessed on: 2026-11-05 - [Agent Zero: First-Run Onboarding](https://www.agent-zero.ai/p/docs/onboarding/) - [Agent Zero: Installation](https://www.agent-zero.ai/p/docs/installation/) - [Agent Zero: model_providers.yaml](https://github.com/agent0ai/agent-zero/blob/main/conf/model_providers.yaml) ## Europe & regional availability Installation instructions and model prerequisites reviewed. The assessment covers the local operating path described; complete country and feature availability of all connected services remains open. Reviewed scope: Local software and documented self-hosting; external services assessed separately Reviewed on: 2026-10-19 ### Self-hosting with own model access With requirements Agent Zero documents operation in your own Docker container on a computer or server. A model provider is configured after startup; its regional availability must be checked separately. Region covered: Europe: own computer or server; model services are country-specific Documented reason: Technical assessment based on installation and provider selection. These sources do not establish a legal cause for regional restrictions. Official source: https://raw.githubusercontent.com/agent0ai/agent-zero/main/README.md ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Agent Zero in a Docker container on your own machine or server with its web interface Sources reviewed: 2026-11-05 ### Account used Documented: You protect the web interface under Settings → Authentication with a username and password. The overview page lists a Secrets feature that lets agents use credentials without exposing them. Evidence: https://www.agent-zero.ai/p/docs/sharing/ Evidence: https://www.agent-zero.ai/p/docs/ ### Admin approval Open in reviewed sources: The reviewed pages do not describe organisation management with administrator approval. Host access is an optional per-instance setting. Evidence: https://www.agent-zero.ai/p/docs/installation/ Evidence: https://www.agent-zero.ai/p/docs/sharing/ ### Data access & team sharing Documented with conditions: The direct Docker command binds the instance to your computer only; the page does not say this for Launcher or other routes. With host access, file edits and commands affect real files on your computer. Projects bundle instructions, files, memory, variables and secrets. Evidence: https://www.agent-zero.ai/p/docs/installation/ Evidence: https://www.agent-zero.ai/p/docs/ ## Prices and included usage Pricing checked: 2026-10-12 MIT-licensed; model and hosting costs are additional. ### Open Source USD 0 license cost MIT license; hosting and model usage are separate. Price source: https://github.com/agent0ai/agent-zero/blob/main/LICENSE Cloud models may incur API costs; local models require your own compute. Pricing details: https://github.com/agent0ai/agent-zero/blob/main/LICENSE ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Agent Zero as a long-running Docker instance with its task scheduler Sources reviewed: 2026-11-05 ### Files and working state Documented: Persistent storage keeps settings, chats, memory, projects and plugins when a container is replaced. If you choose no persistent workspace, deleting the container can also delete its data. Evidence: https://www.agent-zero.ai/p/docs/installation/ ### Sign-ins Open in reviewed sources: The reviewed pages do not describe how long the web sign-in remains valid. Evidence: https://www.agent-zero.ai/p/docs/sharing/ ### Starting further runs Documented: The task scheduler supports recurring tasks via cron, planned one-off times and manual-only tasks. A run uses its own chat context (the default for tasks created in the UI) or a shared one. Evidence: https://www.agent-zero.ai/p/docs/task-scheduler/ ### Human intervention Open in reviewed sources: The scheduler page describes no approval before individual actions, including for tasks the agent creates itself. Host access is an optional per-instance setting that the installation page says to grant only to trusted instances. Evidence: https://www.agent-zero.ai/p/docs/task-scheduler/ Evidence: https://www.agent-zero.ai/p/docs/installation/ ### Detecting errors Documented with conditions: A failed task shows the Error state, and Last Result shows output or error from the last run. As best practice the page advises alerting on failures and mentions execution logs without saying where they are stored. Evidence: https://www.agent-zero.ai/p/docs/task-scheduler/ ### Resuming after failures Documented with conditions: The page does not describe automatic retries. You can stop running tasks and disable tasks; before updates you make a backup and can restore it into a fresh installation. Evidence: https://www.agent-zero.ai/p/docs/installation/ Evidence: https://www.agent-zero.ai/p/docs/task-scheduler/ ### Editorial assessment You run Docker, updates and backups yourself and protect the interface before it is reachable beyond your machine. Failed tasks you have to check actively in the scheduler. ## Memory and conversation continuity Scope: Native memory and separate imported knowledge Sources accessed: 2026-11-04 The memory dashboard supports search and maintenance; provenance distinguishes memories from knowledge imports. ### Storage and scope Partly documented: Memory resides in selectable directories and areas; imported knowledge fragments have separate provenance. The specific backend type is not named here. - [Agent Zero memory guide](https://raw.githubusercontent.com/agent0ai/agent-zero/main/docs/guides/memory.md) ### Selection and timing Partly documented: Persistent agent memory is documented; exact automatic extraction triggers are not specified in the management guide. - [Agent Zero memory guide](https://raw.githubusercontent.com/agent0ai/agent-zero/main/docs/guides/memory.md) - [Agent Zero repository](https://github.com/agent0ai/agent-zero) ### Inspect, edit and delete Documented: The dashboard shows text and metadata, supports editing, deletion and export, and allows selecting the memory directory. - [Agent Zero memory guide](https://raw.githubusercontent.com/agent0ai/agent-zero/main/docs/guides/memory.md) ### Agent and channel boundaries Documented: Global and project memory directories and areas such as fragments and solutions can be distinguished. - [Agent Zero memory guide](https://raw.githubusercontent.com/agent0ai/agent-zero/main/docs/guides/memory.md) ### Retrieval Documented: Memory search offers a similarity threshold, result limit and area filters; imported knowledge can be assessed separately. - [Agent Zero memory guide](https://raw.githubusercontent.com/agent0ai/agent-zero/main/docs/guides/memory.md) ### Session reset and compaction Partly documented: Memories remain available across chats. The exact interaction between conversation compaction and memory is not described here. - [Agent Zero memory guide](https://raw.githubusercontent.com/agent0ai/agent-zero/main/docs/guides/memory.md) - [Agent Zero repository](https://github.com/agent0ai/agent-zero) ## Context Docker and configured model access are required. Official product documentation reviewed. Workflows and assessments are editorial; hands-on product tests are outside the scope of this directory. ## Open points Requirements and limits, not yet confirmed: - Reliability in your workflow ## Sources - https://www.agent-zero.ai/ - https://www.agent-zero.ai/p/docs/ - [Installation - Agent Zero](https://www.agent-zero.ai/p/docs/installation/) - [agent-zero/LICENSE at main · agent0ai/agent-zero](https://github.com/agent0ai/agent-zero/blob/main/LICENSE) ## Provider Provider of the open Agent Zero framework. - Operator: Agent Zero, s.r.o. - Organization: Company - Website: https://www.agent-zero.ai/ - Reviewed: 2026-10-12 - Provider source: https://www.agent-zero.ai/ [Sources and method](https://ki-agentenkompass.de/en/sources/)