Perplexity
Perplexity is selling access to other people's models, and now repricing them weekly.
A side-by-side editorial comparison of LiveKit Agents and Semantic Kernel — release velocity, themes, recent moves, and the top alternatives to consider.
LiveKit Agents ships weekly, and the work is nearly all provider breadth and failure paths.
The two newest entries are bare release tags — 1.6.10 and a 1.6.11 release candidate — with no notes. The releases with content follow one pattern: add speech and avatar vendors (Deepgram Flux, Bland TTS, Spatius avatars, Phonic and Smallest STT options), then fix the ways conversations go wrong. Endpointing and turn detection recur constantly — max_delay held constant under dynamic endpointing, primary speaker preserved through unattributed segments, an Ink-2 speech-onset delay that pushed back STT interruptions. 1.6.8 deprecates the console and dev modes in favour of the lk agent CLI.
Semantic Kernel's releases are now dependency bumps and redirect READMEs pointing users elsewhere.
The .NET and Python packages ship on a steady cadence, but the contents are servicing: SDK and package version bumps, CVE-driven dependency updates, CodeQL suppressions, and HTTP hardening such as disabling automatic redirects in the web plugins. The genuinely functional changes are narrow — a Gemini connector now honoring the configured function choice behavior, an MCP tool approval callback for Azure AI agents shipped as a breaking change, and MCP tools with colliding normalized names being skipped. The latest .NET release removes migrated vector-store providers outright, leaving redirect READMEs behind.
The two newest entries are bare release tags — 1.6.10 and a 1.6.11 release candidate — with no notes. The releases with content follow one pattern: add speech and avatar vendors (Deepgram Flux, Bland TTS, Spatius avatars, Phonic and Smallest STT options), then fix the ways conversations go wrong. Endpointing and turn detection recur constantly — max_delay held constant under dynamic endpointing, primary speaker preserved through unattributed segments, an Ink-2 speech-onset delay that pushed back STT interruptions. 1.6.8 deprecates the console and dev modes in favour of the lk agent CLI.
This is a maintenance train rather than a roadmap: breadth across providers plus relentless correctness work on turn-taking, which is where voice agents actually fail. The one demand on users in the window is the CLI migration. Cadence is roughly weekly and the contributor list is largely external — vendors landing their own plugins.
More provider plugins and more endpointing fixes; the deprecated console and dev modes are the next thing likely to be removed outright.
The .NET and Python packages ship on a steady cadence, but the contents are servicing: SDK and package version bumps, CVE-driven dependency updates, CodeQL suppressions, and HTTP hardening such as disabling automatic redirects in the web plugins. The genuinely functional changes are narrow — a Gemini connector now honoring the configured function choice behavior, an MCP tool approval callback for Azure AI agents shipped as a breaking change, and MCP tools with colliding normalized names being skipped. The latest .NET release removes migrated vector-store providers outright, leaving redirect READMEs behind.
The centre of gravity is moving out of this repository. Vector store providers have migrated to CommunityToolkit packages and their originals are now deleted rather than deprecated, with samples following them across. What remains is maintenance plus the occasional MCP fix, which suggests the agent work that would once have landed here is happening in a different codebase. For teams with Semantic Kernel in production, the signal to read is the removals: each one is a dependency that now resolves somewhere else.
Expect the cadence to continue as security and dependency servicing with occasional MCP fixes, and for migration tooling or documentation pointing at Microsoft Agent Framework to grow faster than any new capability in Semantic Kernel itself.
Other ai-assistants products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either LiveKit Agents or Semantic Kernel.
Perplexity is selling access to other people's models, and now repricing them weekly.
Dosu is folding agent session logs into the knowledge base it already maintains.
Format coverage still outruns hardening — three corrective releases in five days
Copilot ships a model a week; now enterprises get switches for the plugins underneath
ONNX Runtime is dismantling itself into a core plus detachable accelerator plug-ins, CUDA included.
Transformers is becoming a dispatch layer over optimized kernels, and the patches now track vLLM's release calendar.
See all LiveKit Agents alternatives → · See all Semantic Kernel alternatives →
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
They serve adjacent needs but don't currently overlap on shipped themes. LiveKit Agents and Semantic Kernel are shipping at a similar cadence (velocity 5.0 vs 5.0, both within Sparkpulse's "active" band). See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. LiveKit Agents and Semantic Kernel are shipping at a similar cadence (velocity 5.0 vs 5.0, both within Sparkpulse's "active" band). For your specific use case, the alternatives sections above list other ai-assistants products to evaluate alongside.
Top LiveKit Agents alternatives in ai-assistants are ranked by recent ship velocity. Browse the "LiveKit Agents alternatives" section above for the current picks, or visit /alternatives/livekit-agents for the full list with editorial commentary on each.
Top Semantic Kernel alternatives in ai-assistants are ranked by recent ship velocity. Browse the "Semantic Kernel alternatives" section above for the current picks, or visit /alternatives/semantic-kernel for the full list with editorial commentary on each.