{"data":{"slug":"bytedance-deer-flow","name":"deer-flow","tagline":"An open-source long-horizon SuperAgent that handles complex tasks over minutes to hours.","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":80066,"forks":10961,"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":"2026-08-16T04:03:13+00:00","maintenance_label":"Very active","stars_delta_30d":2858,"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":948,"watchers":331,"ai_summary":"bytedance/deer-flow is an advanced AI Agents platform developed in Python. It enables research, coding, and creation through an extensive set of functionalities including sandboxes, memories, tools, skills, subagents, and message gateways for managing lengthy workflows.","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":"2026-08-16T06:01:44.125547+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-framework","name":"agentic-framework"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"langchain","name":"langchain"},{"slug":"multi-agent","name":"multi-agent"},{"slug":"python","name":"python"}],"trust":{"provenance":{"is_fork":false,"github_id":979115477,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-16T06:01:43.183Z","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":2858,"open_issues_delta_30d":-29},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:56:14.416Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-16T06:01:43.805Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-16T06:01:43.805Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-16T06:01:43.805Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to manage lengthy workflows over minutes to hours that require constant supervision or adaptation by the AI agent, deer-flow's long-horizon capabilities make it suitable.","If your project involves deep research tasks, leveraging skills through subagents or integrating complex toolsets for extended processes, choosing this platform can streamline operations with its fine"],"when_not_to_use":["For short, straightforward tasks that do not require extensive workflows (under a minute), deer-flow might be overkill due to its advanced functionalities and setup complexity.","If your team is primarily working with technologies like Node.js or TypeScript rather than Python, other tools might offer better integration and support."],"source":"enrich:decision_facts","observed_at":"2026-07-11T12:00:30.608Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Deer-flow is an advanced SuperAgent platform for handling complex tasks over extended periods with a comprehensive set of functionalities such as sandboxes and memories."}]}}