Agent runtimeAI and agent development

SkVM

Compile, benchmark, and optimize agent skills across different models and runtimes.

Stars
531
Forks
52
License
MIT
Updated
Updated Jul 13, 2026

Checking live repository facts…

Project overview

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.

Repository facts

Primary language
TypeScript
License
MIT
Repository updated
Jul 13, 2026
Default branch
main

Resource types

Agent runtimeBenchmark or evalCLI app

Use cases

AI and agent development

Platforms

OpenClawOpenCode

Operating systems

LinuxmacOS

Runtime

Command lineLocalSandboxed

Capabilities

Verification and evals

Audience

Developers

Related projects

Browse more similar projects