AgentScope
Build and run agents you can see, understand and trust. observed · 2026-08-28
Health v2 · maintenance only
93/100
- Activity 99
- Release rhythm 99
- Longevity 68
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: 11.0
- age_days: 964
- days_rel: 9
- days_push: 7
- n_releases_24m: 41
Adoption not part of the score
29706 stars · 3409 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
AgentScope is a production-ready multi-agent framework for building LLM-powered agents with ReAct reasoning, tool execution, MCP integration, and human-in-the-loop oversight. Version 2.0 adds multi-tenant multi-session management, sandboxed workspaces (local, Docker, E2B, K8s), middleware, and a full-stack SDK with frontend UI and distributed deployment.
Use cases
- build llm agents with tool calling
- create multi-agent systems in python
- run agents with human-in-the-loop approval
- sandbox agent tool execution in docker
- integrate mcp servers with agents
- deploy multi-tenant agent backend
- build chatbot with react reasoning
- stream agent events to a frontend
When to choose
- you need a production-grade agent framework with security, permissions, and sandboxing
- you want multi-tenant, multi-session, or distributed agent deployment
- you need MCP, skills, and tool orchestration with human oversight
- you want a full-stack solution including SDK, UI, and backend
When to avoid
- you rely on AgentScope 1.0 APIs, since 2.0 is a breaking release with no migration path
- you need built-in RAG and long-term memory today, as those modules are still being ported to 2.0
- you only need a lightweight single-prompt LLM call without agent machinery
Facets
framework · maturity active
agent-framework llm-inference mcp chatbot rag middleware large-language-models artificial-intelligence developer-tools python cross-platform self-hosted multi-agent react-agent human-in-the-loop tool-orchestration multi-tenant distributed-agents mcp-client context-management observability sandboxing ai-agents docker kubernetes
6 sources
- readme: https://github.com/agentscope-ai/agentscope · fetched 2026-08-28 · 5216107b171b
- homepage: https://docs.agentscope.io/ · fetched 2026-08-29 · 43bd19a22b37
- site_page: https://docs.agentscope.io/versions/2.0.8dev/en/quickstart · fetched 2026-08-29 · 0120c77fdbe5
- site_page: https://docs.agentscope.io/versions/2.0.8dev/en/others/faq · fetched 2026-08-29 · 10e6d621c070
- site_page: https://docs.agentscope.io/versions/2.0.8dev/en/others/change-log · fetched 2026-08-29 · 98d437b24bad
- registry_pypi: https://pypi.org/pypi/agentscope/json · fetched 2026-08-29 · 0210cc1c9ff4
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| agentscope-ai/agentscope | main | 93 |
| agentscope-ai/agentscope-java | sdk | 83 |
For agents
markdown · JSON · MCP: product_card(name="agentscope-ai/agentscope")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem