Agent runtimeAI and agent development
SkVM
Compile, benchmark, and optimize agent skills across different models and runtimes.
- Stars
- 531
- Forks
- 52
- Updated
- Updated Jul 13, 2026
MIT
Compile, benchmark, and optimize agent skills across different models and runtimes.
SkVM profiles a model-and-agent-runtime combination, compiles a skill against those capabilities, and then evaluates and improves it through precompilation and runtime-optimization workflows. It is aimed at teams that need the same skill to behave across heterogeneous agents rather than tuning prompts by hand for each runtime. Provider configuration is required, and the bundled benchmark suite lives in a separate data submodule.
Resource types
Use cases
Platforms
Run an extensible personal agent and persistent apps on your own devices.
Package AI skills into local agents your team can use from chat.
Operating systems
Runtime
Capabilities
Audience
Public GitHub facts last synced Jul 14, 2026.
Run self-hosted agents and long-lived multi-agent workflows.
Build and govern agent workflows that connect to real business systems.