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.
C-Rank Grade: A (Welcoming) - 57/100
External PR Merge Rate: 57%
Response Time: 2d
First Timer Success: 49%
bytedance/deer-flow has a recorded first-timer success rate of 48.9%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in bytedance/deer-flow respond to incoming external pull requests in approximately 58.6 hours on average. Keeping PRs focused on single tasks and ensuring tests pass helps maintainers review faster.
The C-Rank™ system evaluates GitHub projects on a 0–100 scale using real data: PR merge rates, review turnaround time, active maintainer presence, and first-time contributor success. A score of 57.5 places bytedance/deer-flow in the A tier.
The external contributor pull request merge rate for bytedance/deer-flow is 57.5%, based on public PR activity from non-core contributors.
bytedance/deer-flow currently has 11 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Rigorous architecture standards (72% critical review signals). Ensure PRs strictly follow guidelines before requesting review in bytedance/deer-flow.
Average Response Latency
Tracks hours until a maintainer leaves a review, comment, or PR response.
External Acceptance Rate
Percentage of community pull requests successfully merged into main.
First PR Conversion
Rate at which developers submitting their first repository PR succeed.
Show contributors that your repository actively reviews and merges external pull requests.
[](https://getmerged.abhishekco.de/bytedance/deer-flow?utm_source=github&utm_medium=badge)
Historical health & responsiveness evolution
External PR acceptance
First PR success rate
50% receive response in
90% receive response in
Maintainer review activity heatmap & prime window prediction
Calculating local time...
Calculating local time...
Detected: UTC
Maintainers are most responsive around 11:00 UTC (11:00 UTC in your timezone). Recommended submission window is Tuesday - Thursday from 09:00 to 13:00 UTC (09:00 - 13:00 UTC local).
Limited recent maintainer review activity recorded for this repository. Prediction based on heuristic baseline.
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~38 hours (72% approval). Large PRs (>500 lines) take ~281 hours (26% approval). Keep your diff compact for rapid review.
Enter your branch size and test coverage below to forecast review turnaround and get 1-click git splitting commands.
Alternative open-source projects with active maintainers in Python.
🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.
An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.
FlashInfer: Kernel Library for LLM Serving
Problem DeerFlow 2.0's auth module (JWT / local password / OIDC / session cookie) covers browser-driven, human identity well, but there is no supported way for non-interactive, programmatic callers to access the Gateway API. Any external system that needs to drive DeerFlow server-to-server — CI pipelines, another backend orchestrating batch runs, CLI scripts — currently has to either: script the interactive login flow and manage session cookies (fragile, expiry handling, CSRF dance), or run the Gateway without auth entirely (unsafe for any shared deployment). Use case We run DeerFlow as the agent runtime behind a content-automation platform: an external backend creates threads, starts runs, and polls results over HTTP for 100+ sites on a schedule. These calls must be authenticated, attributable to a specific user (DeerFlow's memory/threads/agents are user-scoped, so identity correctness matters), and individually revocable. Proposal Personal Access Tokens, in the style of GitHub/
Before you start I searched existing issues and this is not a duplicate. Problem / motivation suggest supporting pg schema Proposed solution suggest supporting pg schema Affected area(s) Backend API (gateway / endpoints / SSE) Alternatives considered No response Additional context No response
NAME CPU(cores) MEMORY(bytes) deerflow-backend-674c55c457-dqzjx 14m 395Mi postgres-0 6m 68Mi provisioner-776b74bc67-47grq 3m 91Mi sandbox-37060a71 29m 792Mi sandbox-385fe401 36m 501Mi sandbox-c39325de 32m 582Mi sandbox-f0036078 25m 828Mi
试用deerflow user memory 后台经常碰到memory更新失败，加log看都是 json格式处理失败。建议改成markdown文件保存 feat(memory): refact memory store to markdown， user chat memory经常报错json格式访问 对 tinking 模型response不友好 使用 Markdown 格式替代 JSON 的可行性分析 是的，完全可以！使用 Markdown 格式存储用户 memory 有以下优势： 优点 格式容错性强 - 不像 JSON 那样严格，少一个逗号不会导致整个文件无法解析 便于调试 - 可以直接用文本编辑器查看和修改 LLM 生成更容易 - Markdown 结构更灵活，生成错误的概率更低 人类可读性好 - 直接打开文件就能看到记忆内容 需要修改的部分 存储层 (storage.py) 创建 MarkdownMemoryStorage 类，继承 MemoryStorage 用 Markdown 格式读写文件 Prompt 模板 (prompt.py) 将 MEMORY_UPDATE_PROMPT 改为生成 Markdown 格式 加载/注入逻辑 (prompt.py) format_memory_for_inject
Rate what actually matters after opening a pull request here.
Rate your first-hand PR experience (review speed, maintainer responsiveness, and onboarding ease) to help other contributors.
When evaluating whether to contribute to bytedance/deer-flow, response velocity and maintainer engagement are crucial. GetMerged continuously tracks pull request trajectories, first-comment latency, and code review rounds to help developers avoid submitting pull requests to backlogged repositories.
Currently, maintainers of bytedance/deer-flow acknowledge new external contributions in approximately 2 days+. Out of all submitted pull requests from non-core authors in the last 180-day window, 57.5% were successfully merged into the primary branch.
bytedance/deer-flow has a recorded first-timer success rate of 48.9%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~2 days+. Keeping PRs scoped to single concerns and ensuring CI checks succeed will optimize review turnaround.
The C-Rank™ index scores repositories on a 0 to 100 scale using an objective formula: external PR merge rates, initial response speed, active maintainer count, and first-time contributor retention. A score of 57.5 places bytedance/deer-flow in the Welcoming tier.
The external pull request merge rate is 57.5%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, bytedance/deer-flow currently has 11 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for bytedance/deer-flow are automatically retrieved via the public GitHub API and recalculated daily. Insider pull requests submitted by repository owners or organization members are excluded from merge rate calculations to preserve objective external contributor statistics.