{"data":{"slug":"bytedance-deer-flow","name":"deer-flow","tagline":"An open-source long-horizon SuperAgent harness for research, coding, and creation.","github_url":"https://github.com/bytedance/deer-flow","owner":"bytedance","repo":"deer-flow","owner_avatar_url":"https://avatars.githubusercontent.com/u/4158466?v=4","primary_language":"Python","stars":82626,"forks":11404,"topics":["agent","agentic","agentic-framework","agentic-workflow","ai","ai-agents","deep-research","harness","langchain","langgraph","langmanus","llm","multi-agent","nodejs","podcast","python","superagent","typescript"],"archived":false,"github_pushed_at":"2026-09-18T08:35:17+00:00","maintenance_label":"Very active","stars_delta_30d":2560,"url":"https://www.graphcanon.com/tools/bytedance-deer-flow","markdown_url":"https://www.graphcanon.com/tools/bytedance-deer-flow.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bytedance-deer-flow","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bytedance-deer-flow","description":"An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.","homepage_url":"https://deerflow.tech","license":"MIT","open_issues":874,"watchers":347,"ai_summary":"DeerFlow is an AI-driven SuperAgent harness that uses sandboxes, memories, tools, skills, subagents, and a message gateway to handle tasks ranging from minutes to hours.","readme_excerpt":"## Coding Plan from ByteDance Volcengine\n\n- We strongly recommend using Doubao-Seed-2.0-Code, DeepSeek v3.2 and Kimi 2.5 to run DeerFlow\n- [Learn more](https://www.byteplus.com/en/activity/codingplan?utm_campaign=deer_flow&utm_content=deer_flow&utm_medium=devrel&utm_source=OWO&utm_term=deer_flow)\n- [中国大陆地区的开发者请点击这里](https://www.volcengine.com/activity/codingplan?utm_campaign=deer_flow&utm_content=deer_flow&utm_medium=devrel&utm_source=OWO&utm_term=deer_flow)\n\n---\n\n# PyPI — pin a version for a reproducible deployment\nmake extension-install SOURCE=\"deerflow-extension-acme==1.2.3\"\n\n---\n\n### Improper Deployment May Introduce Security Risks\n\nDeerFlow has key high-privilege capabilities including **system command execution, resource operations, and business logic invocation**, and is designed by default to be **deployed in a local trusted environment (accessible only via the 127.0.0.1 loopback interface)**. If you deploy the agent in untrusted environments — such as LAN networks, public cloud servers, or other multi-endpoint accessible environments — without strict security measures, it may introduce security risks, including:\n\n- **Unauthorized illegal invocation**: Agent functionality could be discovered by unauthorized third parties or malicious internet scanners, triggering bulk unauthorized requests that execute high-risk operations such as system commands and file read/write, potentially causing serious security consequences.\n- **Compliance and legal risks**: If the agent is illegally invoked to conduct cyberattacks, data theft, or other illegal activities, it may result in legal liability and compliance risks.\n\n---\n\n### Deployment Defaults\n\nThe Docker stack publishes its entry port on `127.0.0.1` only, matching the\nlocal-trusted-environment model described above. To reach it from another\nmachine, set `BIND_HOST` in `.env` (e.g. `BIND_HOST=0.0.0.0`) — and only after\nputting the security measures below in place.\n\n**Complete first-run setup before the host becomes reachable.** A fresh\ninstance has no accounts yet, so create the admin account through `/setup`\nimmediately after starting any deployment that is not loopback-only.\n\n---\n\n## License\n\nThis project is open source and available under the [MIT License](./LICENSE).","github_created_at":"2025-05-07T02:50:19+00:00","created_at":"2026-07-07T17:30:43.2953+00:00","updated_at":"2026-09-20T04:32:04.514345+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"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"agentic","name":"agentic"},{"slug":"agentic-framework","name":"agentic-framework"},{"slug":"agentic-workflow","name":"agentic-workflow"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"langchain","name":"langchain"},{"slug":"langgraph","name":"langgraph"},{"slug":"langmanus","name":"langmanus"}],"trust":{"provenance":{"is_fork":false,"github_id":979115477,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:36:35.750Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":0,"last_release_at":"2026-06-25T16:23:22Z","stars_delta_30d":2560,"open_issues_delta_30d":-74},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:36:37.687Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:36:34.599Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:36:34.599Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:36:34.599Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["DeerFlow requires Docker for deployment, with the entry port published on 127.0.0.1 by default to ensure a local trusted environment."],"requires_docker":true},"constraints":{"requires_docker":true},"when_to_use":["Use DeerFlow when you need an AI-driven SuperAgent that can handle complex tasks over long durations, such as deep research or extended coding projects.","Consider DeerFlow if you are working in a local trusted environment where the agent can be deployed securely, as it is designed to be accessible only via the loopback interface by default."],"when_not_to_use":["Avoid using DeerFlow in untrusted environments, such as public cloud servers or LAN networks, without implementing strict security measures, as it poses significant security risks.","Do not use DeerFlow if you cannot ensure that the deployment adheres to compliance and legal standards, as improper deployment can lead to legal liability and risks."],"source":"enrich:decision_facts","observed_at":"2026-09-18T11:05:38.255Z"},"constraint_facets":{"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Requires Docker; DeerFlow requires Docker for deployment, with the entry port published on 127.0.0.1 by default to ensure a local trusted environment."},{"label":"Adopt for","value":"DeerFlow is an AI-driven SuperAgent harness that leverages sandboxes, memories, tools, skills, subagents, and a message gateway to manage tasks over extended periods, from minutes to hours."}]}}