- chore(version): bumping version to 2.0.12dev
- fix(webui): include full calendar days in schedule date filter
- fix(model): normalize nullable usage counters in adapters
- fix(tool): keep resolvable annotations when one hint fails
- fix(app): remove server-path skill import endpoint
- fix(tts): keep CosyVoice cold-start buffer when the send fails
AgentScope by Alibaba (Tongyi Lab)
A Python framework for building multi-agent applications with ReAct agents, tool and MCP management, model abstractions, pipelines and human-in-the-loop controls.
Use it in: API / SDK Self-hosted Web app Works with: MCP Local models Multi-agent
On this page
Usage data: latest readings Nov 19 to Nov 21, 2026, last checked Nov 21, 06:27 UTC. Date of each number
What AgentScope does
AgentScope is an open-source multi-agent framework from Alibaba, first released in January 2024. You use it through an SDK, self-hosted and a web app. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from OpenAI, Anthropic, Google, Qwen, DeepSeek and xAI. It is used from Python. It is free and open source (Apache-2.0); you pay only for the models it calls.
Key facts
| Maker | Alibaba (Tongyi Lab) |
|---|---|
| Type | Open-source multi-agent framework |
| First released | January 2024 |
| License | Apache-2.0 |
| Interfaces | SDK, Self-hosted, Web app |
| Main language | Python |
| Open issues and PRs | 836 |
Pricing
Free and open source (Apache-2.0).
Source: official pricing page, checked Oct 6, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (Apache-2.0)
- Where you use itSDK, Self-hosted, Web app
- Supports MCP?Yes
- Model providersopenai, anthropic, google, qwen, deepseek, xai, local
- Subagents / multi-agent?Yes
- Feature comparisonAll agents
- Closest alternativeLangChain · all alternatives
What's new in AgentScope: November 2026 so far
November brought focused improvements to core functionality, with fixes addressing calendar filtering, model adapters, tool annotations, and multimodal embedding caching.
- Calendar date filters now include full days in the schedule interface
- Model adapter usage counters properly handle null values
- Tool annotations remain resolvable even when one hint fails
- Embedding cache settings now honored on the Gemini multimodal path
1 release this month · summarised from the official release notes · all months
AgentGid articles about AgentScope
Best AI Agent Frameworks in 2026: LangGraph, CrewAI, OpenAI Agents SDK and More
The AI agent frameworks developers actually use, ranked on live downloads and GitHub data, with a plain guide to which one fits Python, TypeScript, multi-agent or Microsoft-stack work.
How to Build an AI Agent: No-Code Builders, Frameworks and SDKs
A practical guide to building your first AI agent: choosing between no-code builders, open-source frameworks and model vendors' SDKs, the core agent loop, tools, guardrails and testing, with live usage data for each option.
AI Agent Statistics 2026: Live Usage, Growth and Activity Data
Current statistics on AI agents from public data: package downloads, editor installs, GitHub stars, pull requests opened by coding agents, release pace and benchmark results. Updated daily.
Get started with AgentScope
| PyPI | pip install agentscope |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Add-ons for AgentScope: save tokens, add memory and tools
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for AgentScope or for agent frameworks in general. Savings and results depend on your workload.
AgentScope alternatives
Best AgentScope alternatives compared · All agent frameworks and SDKs
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
LangChainLangChain |
79 | 41.8M | up 6.5% | down 2.6% | 150K+81/day | 1.5.23d ago | Free (OSS) | |||
| 2 |
LangGraphLangChain |
75 | 20.6M | up 8.5% | up 27.0% | 45.2K+44/day | 1.2.24yesterday | Free (OSS) | |||
| 3 |
AI SDKVercel |
67 | 48.7M | up 8.6% | up 35.7% | 28.1K+28/day | 7.0.179yesterday | Free (OSS) | |||
| 4 |
Claude Agent SDKAnthropic |
64 | 30.7M | up 10.6% | up 36.3% | 8,606+10/day | 0.2.187yesterday | Free (OSS) | |||
| 5 |
MastraMastra |
64 | 4.1M | up 29.1% | up 49.1% | 29.7K+30/day | 1.84.03d ago | Free (OSS) | |||
| 6 |
OpenAI Agents SDKOpenAI |
62 | 7.3M | up 8.3% | up 36.6% | 30.8K+21/day | 0.25.03d ago | Free (OSS) | |||
Tools used with AgentScope
What 124 public GitHub projects that depend on AgentScope use with it, from their dependency files.
- python-dotenv66.9%
- Pydantic55.6%
- Uvicorn54.8%
- FastAPI46.8%
- OpenAI Python Library45.2%
- PyYAML37.9%
- Requests37.9%
- NumPy33.1%
- Rich28.2%
- pandas27.4%
Used far more often here than in AI-built projects overall: what sets AgentScope projects apart.
- DashScope SDK22.6% · 235.4×
- shortuuid18.5% · 165.7×
- json5 (Python)12.1% · 126.1×
- docstring-parser12.1% · 58.2×
- json-repair14.5% · 50.4×
- python-socketio12.1% · 50.4×
- websocket-client12.1% · 42.0×
- DDGS12.1% · 39.8×
Ratings from people who use AgentScope
No ratings yet. Used AgentScope? Rate it and say what it is good and bad at.
AgentScope news
-
AgentScope 2.0.12 released
chore(version): bumping version to 2.0.12dev; fix(webui): include full calendar days in schedule date filter; fix(model): normalize nullable usage counters in adapters
-
AgentScope downloads up 83% in a week
141K PyPI downloads in the 7 days to Nov 12, against 77.3K the week before.
What changed: recent AgentScope releases
7 stable releases in the last 90 days · Monthly summary · Full changelog
- fix(model): declare real WAV sizes in the final streamed audio block
- fix(embedding): isolate Ollama embedding caches by host
- fix(model): await provider stream cleanup on public aclose
- fix(workspace): offload nested media from context archives
- feat(tui): add right arrow key to switch questions in ask user ui
- feat(asr): add batch transcription abstraction and OpenAI model
Earlier releases
- chore(version): bump version to 2.0.10dev
- docs: announce SOP, TeamPipeline and MiniMax support in news
- fix(tts): label audio with the effective response format
- fix(model): emit the dashscope audio transcript as text
- fix(rag): preserve omitted Word table columns
- fix(rag): preserve duplicate and blank Excel headers
- Standard Operating Procedures (Experimental): Added the agentscope.sop module for splitting a task into ordered milestones, each verified before the next one starts, with run state that can be…
- Team Pipeline: Added a TeamPipeline class where a leader agent delegates tasks to member agents, which run concurrently and hand their results back.
- More Realtime Voice Models: Added OpenAI Realtime, Gemini Live, and xAI Grok Voice models to the realtime voice agent.
- Terminal UI: Introduced the agentscope.tui module, a full-screen terminal interface for chatting with agents and running realtime voice sessions via launch_realtime_ui.
- AskUser Tool: Added AskUser, an external tool that lets agents ask users multiple-choice questions.
- MiniMax Model and Jev-based Model Routing: Added the MiniMax chat model (M3 by default), and a ModelRouterMiddleware backed by the new agentscope.classifier module (with Jev support) that picks…
- Realtime Voice Agent: Introduced a realtime voice agent with DashScope backends and local transport support.
- A2A Protocol Support: Added A2AAgent class to the agent module, enabling agent-to-agent communication.
- New Pipeline Module: Added a new pipeline module with a GoalPipeline class for goal-driven agent workflows.
- Agent-Driven Context Compression: Introduced a context compression tool that allows agents to manage their own context window.
- LLM Rerank for RAG: Added LLM-based reranking support to improve RAG retrieval quality.
- Volcengine Ark Model: Added support for Volcengine Ark chat model.
- fix(formatter): derive audio format from media type
- fix(gemini): exclude tool-execution tokens from output_tokens
- feat(formatter): use native multimodal tool outputs
- docs(examples): fix broken relative link to _types.py in mem0 README
- feat(pipeline): add new pipeline module and a GoalPipeline class
- fix(webui): isolate sessions when switching agents
AgentScope prices over time
AgentScope popularity and usage data
AgentScope was downloaded 146K times from PyPI in the week ending Nov 19, 2026, up 3.5% on the week before and up 223.1% over the last 30 days compared with the 30 before. Its download count moved to a different level overnight on Sep 15, 2026. A jump like that comes from automated installs switching on or off or from a change in how the registry counts, so growth rates across that date are not shown. The GitHub repository has 36.4K stars, 2,873 of them added in the last 30 days. The latest stable release is 2.0.12, published Nov 16, 2026; there were 2 stable releases in the past 30 days.
Download the raw daily series: agentscope.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 19, 2026 | Nov 21, 06:24 UTC |
| GitHub stars | Nov 21, 2026 | Nov 21, 06:26 UTC |
| Website rank (Tranco) | Nov 20, 2026 | Nov 21, 06:27 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
AgentScope FAQ
How much does AgentScope cost?
Free and open source (Apache-2.0).
Is AgentScope open source?
Yes. AgentScope is open source, released under the Apache-2.0 license.
How popular is AgentScope?
AgentScope was downloaded 146K times from PyPI in the week ending Nov 19, 2026, up 3.5% on the week before and up 223.1% over the last 30 days compared with the 30 before. Its download count moved to a different level overnight on Sep 15, 2026. A jump like that comes from automated installs switching on or off or from a change in how the registry counts, so growth rates across that date are not shown. The GitHub repository has 36.4K stars, 2,873 of them added in the last 30 days.
What is the latest version of AgentScope?
The latest stable release we track is 2.0.12, published on Nov 16, 2026.
What are the alternatives to AgentScope?
The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.
For the makers of AgentScope badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/agentscope/)
[](https://agentgid.com/agents/agentscope/)
[](https://agentgid.com/agents/agentscope/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
PyPI: agentscope. GitHub: agentscope-ai/agentscope. Site rank: agentscope.io on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: github.com, pypi.org.