Item detail

github.com

agentscope-ai/agentscope

RepoRadar surfaced agentscope-ai/agentscope — a developer tool — into the AI Agent Framework section, where it sits at Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 10.0 out of 10.

Open on GitHub →Back to radar

Score9.2

Popularity92.0

Riskconditional

TierGold

Score breakdown

Usefulness9.0

Novelty8.0

Momentum8.0

Maturity9.0

Open-source/build8.4

Evidence7.2

Workflow potential10.0

Setup ease4.2

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Use AgentScope when you need structured handoffs, reusable agent primitives, and observable orchestration instead of ad-hoc scripts.

Who should use it

teams building production LLM agent platforms teams standardizing MCP/tool-connected workflows developers prototyping coordinated agent pipelines

Who should skip it

Move on from agentscope-ai/agentscope if the licensing terms, language support, or platform requirements do not fit your project.

About this signal

agentscope-ai/agentscope is tracked by RepoRadar as a developer tool in the AI Agent Framework section. First seen 2026-06-18; the source record was last checked on 2026-06-18. The current verdict is 'try now' with a Gold tier and advanced setup difficulty. The standout signals for agentscope-ai/agentscope are workflow potential (10.0) and practical usefulness (9.0), while setup ease (4.2) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The agentscope-ai/agentscope record combines a 9.2/10 composite score with separate popularity (92.0), risk (conditional), and setup (advanced) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

Agent runtimes can call external APIs and services; constrain credentials per tool and enforce idempotency for retries; Advanced orchestration patterns have a steeper onboarding curve than single-agent wrappers.

Evidence links

github.com

Closest alternatives / related signals

agents agent-framework mcp orchestration python

Verification record

What RepoRadar actually verified

Tested in a bounded workflow

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-14T00:53:02.984902Z.

passed · cohort-20260713-agentscope-local-toolkit-workflow

Tester: RepoRadar automated local verification harness
Started: 2026-07-14T00:52:56.902951Z
Completed: 2026-07-14T00:53:02.984902Z
Environment: Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time: 1 minute(s)
Evidence scope: Bounded representative workflow
Cleanup: Per-check temporary home and work directory removed. Shared cohort package cache removed.

Actions exercised

Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
Created 1 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
Wrapped a deterministic typed Python function in AgentScope's FunctionTool and registered it in a Toolkit.
Inspected the generated function schema, executed the tool locally, and asserted the normalized checkout incident routed to platform-oncall.
Executed bounded check: Register a typed incident-routing tool with AgentScope, inspect the generated schema, and execute it against a synthetic incident.
Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 6.08-second wall time.

Observed results

Command exited 0 after 6.08 seconds.
AgentScope generated the required service/severity schema and returned the exact normalized routing payload through its local tool adapter.
Expected marker 'CHECK_OK tool=route_incident queue=platform-oncall severity=4 schemas=1' was observed in retained output.
Validated result.json: 4 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.

Observed strengths

The framework's tool abstraction converted typed Python input into a machine-readable schema and a normalized ToolChunk result without a model or account.

Friction

AgentScope 2.0.4 resolved 89 Python packages for this small model-free path; broader agent execution would add model, formatter, permission, and context configuration.
Setup or runtime emitted 17 stderr line(s); the complete warnings/errors are preserved in the retained log.

Limitations

This model-free toolkit path does not run an AgentScope agent loop, model adapter, memory, MCP client, permission prompt, multi-agent workflow, or hosted service.
This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The pinned AgentScope 2.0.4 package and local function tool used no paid model, hosted AgentScope service, or authenticated provider.

Privacy assessment: Only a synthetic service name and severity were processed in the disposable Python process; no model, MCP server, telemetry target, or external data service received them.

Open retained test log →

Verification sources

Official source ↗ · checked 2026-08-13

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

47 dated snapshots retained from 2026-06-18 through 2026-08-13; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score9.2 current · +0.0 net

Repository momentum9.6 current · +1.6 net

GitHub stars (observed)28,918 current · +1,091 net

GitHub stars28,918 exact observation

Versionv2.0.6

Last release2026-08-07T10:39:34Z

Maintenanceactive

Current riskconditional

Current verdicttry now

Pricing baselineNo structured commercial pricing baseline

Pricing checkedNot applicable or not recorded

Pricing freshnessNo dated commercial pricing review

Integrations baselineModel Context Protocol

Recent dated points

Date	Score	Momentum	Stars	Risk	Verdict	Maintenance
2026-08-13	9.2	9.6	28,918	conditional	try now	active
2026-08-12	9.2	9.6	28,873	conditional	try now	active
2026-08-11	9.2	9.6	28,817	conditional	try now	active
2026-08-10	9.2	9.6	28,767	conditional	try now	active
2026-08-09	9.2	9.6	28,733	conditional	try now	active
2026-08-08	9.2	9.6	28,713	conditional	try now	active
2026-08-07	9.2	9.6	28,519	conditional	try now	active
2026-08-06	9.2	8.0	Not recorded	conditional	try now	not recorded
2026-08-05	9.2	8.0	Not recorded	conditional	try now	not recorded
2026-08-04	9.2	9.6	28,519	conditional	try now	active
2026-08-03	9.2	9.6	28,519	conditional	try now	active
2026-08-02	9.2	9.3	28,482	conditional	try now	active

Why the record changed

stars changed2026-08-13

Stars changed: 28873 → 28918.

stars changed2026-08-12

Stars changed: 28817 → 28873.

stars changed2026-08-11

Stars changed: 28767 → 28817.

stars changed2026-08-10

Stars changed: 28733 → 28767.

stars changed2026-08-09

Stars changed: 28713 → 28733.

stars changed2026-08-08

Stars changed: 28519 → 28713.

version changed2026-08-08

Version changed: v2.0.5 → v2.0.6.

stars changed2026-08-03

Stars changed: 28482 → 28519.

stars changed2026-08-02

Stars changed: 28472 → 28482.

stars changed2026-08-01

Source-observed stars changed: 28463 → 28472. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed2026-07-29

Stars changed: 28346 → 28390.

stars changed2026-07-28

Source-observed stars changed: 28332 → 28346. This reports the retained observation delta and does not infer why the upstream change occurred.