{"data":{"slug":"agent0ai-agent-zero","name":"agent-zero","tagline":"Agent Zero AI framework","github_url":"https://github.com/agent0ai/agent-zero","owner":"agent0ai","repo":"agent-zero","owner_avatar_url":"https://avatars.githubusercontent.com/u/216033749?v=4","primary_language":"Python","stars":18906,"forks":3746,"topics":["agent","ai","assistant","autonomous","linux","zero"],"archived":false,"github_pushed_at":"2026-08-16T17:45:50+00:00","maintenance_label":"Very active","stars_delta_30d":453,"url":"https://www.graphcanon.com/tools/agent0ai-agent-zero","markdown_url":"https://www.graphcanon.com/tools/agent0ai-agent-zero.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/agent0ai-agent-zero","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=agent0ai-agent-zero","description":"Agent Zero AI framework","homepage_url":"https://agent-zero.ai","license":"Other","open_issues":156,"watchers":287,"ai_summary":"Agent Zero is an AI framework that creates Dockerized instances for autonomous AI agents. It supports integration with LLM providers like OpenAI Codex through OAuth.","readme_excerpt":"## A0 Install\n\nUse **A0 Install** when you want the terminal path: SSH sessions, servers, recovery shells, or a scriptable setup. It creates Dockerized Agent Zero instances, mounts each instance's data into `/a0/usr` inside the container, and uses a reuse-before-setup policy: it tries your current Docker CLI configuration, `DOCKER_HOST`, Docker contexts, and known local Docker-compatible endpoints before setting up a runtime.\n\n---\n\n## Docker already installed? Run this directly\n\n```bash\ndocker run -p 80:80 -v a0_usr:/a0/usr agent0ai/agent-zero\n```\n\nOpen the Web UI, configure your LLM provider, and start with a concrete task. For the full setup and onboarding experience, see the [Installation guide](./docs/setup/installation.md).\n\n</details>\n\n---\n\n## Use Your OpenAI Codex Plan\n\n<img alt=\"OAuth LLM plans in Agent Zero\" src=\"docs/res/codex-screenshot.png\" />\n<br>\n\nAgent Zero connects to your OpenAI Codex plan through the new OAuth flow. Sign in with your account, pick the Codex-backed provider, and let Agent Zero use the plan you already have. Click \"Connect\", enter the device code in the OpenAI page, choose your model, and you're set.\n\nThis is the first step toward account-backed LLM plans in Agent Zero. More integrations are coming, including Gemini CLI and Claude Code through extra-usage.","github_created_at":"2024-06-10T09:10:45+00:00","created_at":"2026-07-07T17:38:47.068052+00:00","updated_at":"2026-09-30T23:32:56.229712+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"ai","name":"ai"},{"slug":"assistant","name":"assistant"},{"slug":"autonomous","name":"autonomous"},{"slug":"docker","name":"docker"},{"slug":"linux","name":"linux"},{"slug":"openai","name":"openai"},{"slug":"zero","name":"zero"}],"trust":{"provenance":{"is_fork":false,"github_id":812975380,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-19T06:01:00.011Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":15,"days_since_push":2,"last_release_at":"2026-08-12T13:58:33Z","stars_delta_30d":453,"open_issues_delta_30d":-67},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":99,"high_count":0,"last_scan_at":"2026-07-11T11:13:08.050Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-19T06:01:00.508Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-19T06:01:00.508Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-19T06:01:00.508Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use Agent Zero when you need to create Dockerized instances for autonomous AI agents that can be easily managed and scaled.","Choose Agent Zero if you require integration with LLM providers such as OpenAI Codex through OAuth, allowing you to leverage your existing LLM plans.","Opt for Agent Zero when you need a framework that supports a reuse-before-setup policy, which tries to use your current Docker CLI configuration before setting up a new runtime."],"when_not_to_use":["Avoid Agent Zero if you do not require Dockerization for your AI agents, as it adds an extra layer of complexity that may not be necessary.","Do not use Agent Zero if you are looking for a framework that supports a wide range of LLM providers beyond OpenAI Codex, as its current integration is limited.","Skip Agent Zero if you prefer a setup that does not rely on OAuth for connecting to LLM providers, as it may introduce additional steps in the setup process."],"source":"enrich:decision_facts","observed_at":"2026-09-30T23:32:52.518Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Agent Zero is a Python-based AI framework that facilitates the creation of Dockerized autonomous AI agents, integrating with LLM providers like OpenAI Codex via OAuth."}]}}