Build and run agents you can see, understand and trust.
C-Rank Grade: A (Welcoming) - 67/100
External PR Merge Rate: 45%
Response Time: -
First Timer Success: 35%
agentscope-ai/agentscope has a recorded first-timer success rate of 34.8%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in agentscope-ai/agentscope 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 67.2 places agentscope-ai/agentscope in the A tier.
The external contributor pull request merge rate for agentscope-ai/agentscope is 45.5%, based on public PR activity from non-core contributors.
agentscope-ai/agentscope currently has 15 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Rigorous architecture standards (80% critical review signals). Ensure PRs strictly follow guidelines before requesting review in agentscope-ai/agentscope.
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/agentscope-ai/agentscope?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 03:00 UTC (03:00 UTC in your timezone). Recommended submission window is Wednesday - Friday from 02:00 to 06:00 UTC (02:00 - 06:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~16 hours (57% approval). Large PRs (>500 lines) take ~115 hours (20% approval). Keep your diff compact for rapid review.
Background Context management for RealtimeAgent differs fundamentally from the standard Agent class: Runtime context is maintained on the API side, not locally On session recovery, context must be re-injected — either merged into the system prompt/instructions, or replayed as text messages to the model. This implies a summarization step: a compressed summary of prior context should be prepended to the system prompt when resuming a session Compressed context segments should be offloaded to a local workspace, consistent with how Agent handles this Truncation strategy for tool results should align with the existing Agent behavior Two open questions to resolve before implementation: Token counting: Realtime APIs may not expose token usage in the same way as standard chat APIs — the counting mechanism needs to be clarified first, as it gates the truncation/compression trigger Compression timing: Unlike Agent, compression in RealtimeAgent can potentially run concurrently with the ong
Background Through recent investigation into RAGFlow, we found that it provides a complete, end-to-end RAG pipeline — including document parsing, chunking, indexing, and retrieval — as a fully managed solution. This makes it fundamentally different from a traditional vector database (VDB). Forcing RAGFlow into our existing VDB abstraction would be a poor fit: it would either require bypassing RAGFlow's core strengths (e.g., its built-in document processing and indexing pipeline) or lead to an awkward, leaky abstraction. To fully leverage what RAGFlow offers, it should instead be integrated at the Knowledge layer, sitting alongside the existing Knowledge class rather than beneath it. Changes Add RAGFlowKnowledge class under the rag module Implement the same interface as the existing Knowledge class, ensuring consistency and interoperability across different knowledge backends Encapsulate RAGFlow's document parsing, indexing, and retrieval capabilities within the new class
Background The channel system in Agent Service currently supports Feishu and Discord. Slack is one of the most widely used team collaboration platforms in enterprise environments, and adding Slack channel support will make Agent Service more accessible in professional and developer-oriented workflows. Changes Add a new SlackChannel class under agentscope.app.channel module (inherited from ChannelBase), considering to support (depends on the Slack API side): ListChats: list all available channels/conversations accessible by the bot ListChatMembers: list all members in a specified channel or conversation SendMessage: send a text message to a specified channel or user SendFile: send a file attachment to a specified channel or user SendImage: send an image to a specified channel or user More tools to be considered based on the capabilities provided by the Slack API
Background The channel system in Agent Service currently supports Feishu and Discord. Telegram is a widely adopted messaging platform with a well-established bot API, making it a natural fit for agent-based interactions. Adding Telegram channel support will extend the reach of Agent Service to a large international user base. Changes Add a new TelegramChannel class under agentscope.app.channel module (inherited from ChannelBase), considering to support (depends on the Telegram Bot API side): ListChats: list all available chats accessible by the bot ListChatMembers: list all members in a specified chat SendMessage: send a text message to a specified chat or user SendFile: send a file attachment to a specified chat or user SendImage: send an image to a specified chat or user More tools to be considered based on the capabilities provided by the Telegram Bot API
Background The channel system in Agent Service currently supports Feishu and Discord. WhatsApp is one of the most widely used messaging platforms globally, and adding WhatsApp channel support will significantly broaden the reach of Agent Service in international and consumer-facing scenarios. Changes Add a new WhatsAppChannel class under agentscope.app.channel module (inherited from ChannelBase), considering to support (depends on the WhatsApp Business API side): ListChats: list all available conversations accessible by the bot ListChatMembers: list all members in a specified conversation SendMessage: send a text message to a specified user or group SendFile: send a file attachment to a specified user or group SendImage: send an image to a specified user or group More tools to be considered based on the capabilities provided by the WhatsApp Business API
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 agentscope-ai/agentscope, 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 agentscope-ai/agentscope acknowledge new external contributions in approximately -. Out of all submitted pull requests from non-core authors in the last 180-day window, 45.5% were successfully merged into the primary branch.
agentscope-ai/agentscope has a recorded first-timer success rate of 34.8%. 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 67.2 places agentscope-ai/agentscope in the Welcoming tier.
The external pull request merge rate is 45.5%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, agentscope-ai/agentscope currently has 15 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for agentscope-ai/agentscope 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.