Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
C-Rank Grade: A (Welcoming) - 64/100
External PR Merge Rate: 56%
Response Time: -
First Timer Success: 42%
HKUDS/nanobot has a recorded first-timer success rate of 42.0%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in HKUDS/nanobot respond to incoming external pull requests in approximately 0.0 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 64.1 places HKUDS/nanobot in the A tier.
The external contributor pull request merge rate for HKUDS/nanobot is 55.8%, based on public PR activity from non-core contributors.
HKUDS/nanobot currently has 2 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Balanced & professional review environment in HKUDS/nanobot. Maintains strict focus on technical quality and test standards.
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/HKUDS/nanobot?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 06:00 UTC (06:00 UTC in your timezone). Recommended submission window is Tuesday - Thursday from 05:00 to 09:00 UTC (05:00 - 09:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~16 hours (70% approval). Large PRs (>500 lines) take ~115 hours (25% approval). Keep your diff compact for rapid review.
Problem muse-spark-1.3-contributor / muse-spark-1.2-contributor on opencode.ai/zen/go/v1 require the OpenAI Responses wire format (/responses). The gateway's /chat/completions route returns 500 for them (see anomalyco/opencode#47349, anomalyco/opencode#44659). In nanobot The opencode_go provider is hardcoded to Chat Completions: openai_compat_provider.py:536 forces api_type="auto" for any provider other than openai config/schema.py rejects api_type: "responses" for providers.opencodeGo (raises ValueError) So muse-spark is unusable through nanobot — requests fail with 503 endpoint is unavailable (the gateway's chat/completions route for these models is broken upstream). Local workaround that works Adding responses_models=("muse-spark-1.3-contributor", "muse-spark-1.2-contributor") to the opencode_go ProviderSpec in providers/registry.py routes those models through the existing /responses implementation (_should_use_responses_api → model_responses), and muse-spark works. Request Of
需求描述 在 WebUI 中，当一次 agent turn 执行完成后，如果用户当前正在该页面上，播放一个通知铃声提醒。 使用场景 用户在 WebUI 页面中等待 agent 执行较长任务（工具调用、文件编辑、shell 命令等） 任务完成后，页面没有明显提示，用户不知道已经回复完毕 需要刷新页面或盯着屏幕才能发现新消息 期望行为 默认关闭，在 Settings 中提供开关（"WebUI notification sound" 或类似名称） 开启后，每次 agent turn 完成时播放一个短促的通知音 声音文件使用 WebUI 内置的静态资源（不依赖外部 URL），或提供一个可配置的音频文件路径 仅对当前激活的 WebUI 标签页播放（利用 Page Visibility API，页面不可见时不播放） 不影响其他 channel（Telegram/飞书等）的通知逻辑 技术参考 前端：WebUI 使用 WebSocket 接收消息，可以在 turn 完成事件处触发 Audio 播放 后端：Settings 中新
With the latest update and the removal of litellm_provider.py the integration with langchain.com does not work anymore. Any ideas how to fix this?
Problem Users running Nanobot with custom gateways or paid API providers currently have no visibility into token usage or costs. The session files store conversations but don't capture usage metadata that many API responses include. Proposed Solution Add a simple usage logging mechanism that: Captures usage data from API responses - Many LLM APIs return usage data (prompt tokens, completion tokens, total tokens). Store this in a structured format. Logs to a dedicated file - Create a usage log (e.g., logs/usage.jsonl or logs/usage.csv) with entries containing: Timestamp Model used Prompt tokens Completion tokens Total tokens Estimated cost (optional, based on configured rates) Minimal overhead - Implementation should be lightweight and not slow down conversations. Benefits Cost visibility: Users can track spending over time Model comparison: See which models are used most frequently Budget management: Set alerts or limits based on actual usage Analytics: Understand usage patt
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 HKUDS/nanobot, 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 HKUDS/nanobot acknowledge new external contributions in approximately -. Out of all submitted pull requests from non-core authors in the last 180-day window, 55.8% were successfully merged into the primary branch.
HKUDS/nanobot has a recorded first-timer success rate of 42.0%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~-. 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 64.1 places HKUDS/nanobot in the Welcoming tier.
The external pull request merge rate is 55.8%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, HKUDS/nanobot currently has 2 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for HKUDS/nanobot 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.