Item detail

github.com

microsoft/semantic-kernel python-1.43.1

microsoft/semantic-kernel python-1.43.1 is a framework in RepoRadar's AI Agent Frameworks section, holding Silver tier and a 'watch' verdict. Its strongest signal is workflow potential, scored 8.5 out of 10.

Open on GitHub →Back to radar

Score7.7

Popularity84.0

Riskconditional

TierSilver

Score breakdown

Usefulness7.0

Novelty6.0

Momentum7.0

Maturity7.4

Open-source/build8.4

Evidence7.2

Workflow potential8.5

Setup ease6.2

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

Why it matters

A relevant update for teams standardizing enterprise agent SDKs around Microsoft ecosystems and function-calling workflows.

Who should use it

enterprise AI teams function-calling architects Azure/OpenAI integrators

Who should skip it

Consider microsoft/semantic-kernel python-1.43.1 lower priority if you already have a working solution in this category.

About this signal

microsoft/semantic-kernel python-1.43.1 is tracked by RepoRadar as a framework in the AI Agent Frameworks section. First seen 2026-06-18; the source record was last checked on 2026-06-18. The current verdict is 'watch' with a Silver tier and intermediate setup difficulty. The standout signals for microsoft/semantic-kernel python-1.43.1 are workflow potential (8.5) and open-source/build quality (8.4), while novelty (6.0) 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 microsoft/semantic-kernel python-1.43.1 record combines a 7.7/10 composite score with separate popularity (84.0), risk (conditional), and setup (intermediate) 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

Framework updates in enterprise environments can change function-calling behavior; re-run tool permission and output-schema tests before broad rollout.

Evidence links

github.com

Closest alternatives / related signals

semantic-kernel agent-framework azure function-calling enterprise

Verification record

What RepoRadar actually verified

Tested in a bounded workflow

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-13T10:36:43.118028Z.

passed · cohort-20260712-semantic-kernel-native-plugin-workflow

Tester: RepoRadar automated local verification harness
Started: 2026-07-13T10:36:34.959906Z
Completed: 2026-07-13T10:36:43.118028Z
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.
Decorated a typed native method as a Semantic Kernel function and registered its object as an operations plugin.
Invoked the plugin by plugin/function name with severity 4, asserted page, and retained resolved metadata.
Executed bounded check: Register and invoke a typed native Semantic Kernel incident-routing plugin.
Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 8.16-second wall time.

Observed results

Command exited 0 after 8.16 seconds.
Semantic Kernel discovered one operations plugin and invoked its typed route function with the expected page result.
Expected marker 'CHECK_OK plugins=1 function=route result=page' was observed in retained output.
Validated result.json: 3 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.

Observed strengths

Native plugins can be registered, addressed, and invoked through the same kernel surface without requiring an AI connector.

Friction

The pinned SDK currently requires prerelease Azure dependency resolution even though this local native-function workflow uses no Azure service.
Setup or runtime emitted 11 stderr line(s); the complete warnings/errors are preserved in the retained log.

Limitations

The native plugin path validates plugin discovery and invocation without AI services; it does not test planners, prompt functions, model connectors, memory, or process frameworks.
This credential-free disposable workflow does not establish production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The native plugin invocation was local and used no Microsoft, Azure, model, or hosted-memory service.

Privacy assessment: Only a synthetic integer traversed the local Kernel and plugin; no connector, telemetry service, or network endpoint was configured.

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 score7.7 current · +0.0 net

Repository momentum9.3 current · +2.3 net

GitHub stars (observed)28,447 current · +139 net

GitHub stars28,447 exact observation

Versionpython-1.44.1

Last release2026-08-06T09:54:50Z

Maintenanceactive

Current riskconditional

Current verdictwatch

Pricing baselineNo structured commercial pricing baseline

Pricing checkedNot applicable or not recorded

Pricing freshnessNo dated commercial pricing review

Integrations baselineOpenAI

Recent dated points

Date	Score	Momentum	Stars	Risk	Verdict	Maintenance
2026-08-13	7.7	9.3	28,447	conditional	watch	active
2026-08-12	7.7	9.3	28,444	conditional	watch	active
2026-08-11	7.7	9.3	28,439	conditional	watch	active
2026-08-10	7.7	9.3	28,437	conditional	watch	active
2026-08-09	7.7	9.3	28,433	conditional	watch	active
2026-08-08	7.7	9.3	28,429	conditional	watch	active
2026-08-07	7.7	9.3	28,408	conditional	watch	active
2026-08-06	7.7	7.0	Not recorded	conditional	watch	not recorded
2026-08-05	7.7	7.0	Not recorded	conditional	watch	not recorded
2026-08-04	7.7	9.3	28,408	conditional	watch	active
2026-08-03	7.7	9.3	28,408	conditional	watch	active
2026-08-02	7.7	9.3	28,401	conditional	watch	active

Why the record changed

stars changed2026-08-13

Stars changed: 28444 → 28447.

stars changed2026-08-12

Stars changed: 28439 → 28444.

stars changed2026-08-11

Stars changed: 28437 → 28439.

stars changed2026-08-10

Stars changed: 28433 → 28437.

stars changed2026-08-09

Stars changed: 28429 → 28433.

version changed2026-08-08

Version changed: dotnet-1.78.0 → python-1.44.1.

stars changed2026-08-08

Stars changed: 28408 → 28429.

stars changed2026-08-03

Stars changed: 28401 → 28408.

stars changed2026-08-02

Stars changed: 28399 → 28401.

stars changed2026-08-01

Source-observed stars changed: 28398 → 28399. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed2026-07-29

Stars changed: 28378 → 28385.

stars changed2026-07-28

Stars changed: 28320 → 28378.