Engineering writing about systems-language agent runtimes, native-binary deployment of AI agents, and the design behind tokenworm.https://tokenworm.neullabs.com/en-ushttps://tokenworm.neullabs.com/blog/when-systems-languages-start-winning-the-agent-layer/https://tokenworm.neullabs.com/blog/when-systems-languages-start-winning-the-agent-layer/The first wave of AI agent SDKs is Node and Python. That made sense — the model APIs were Python-shaped and the audience was data scientists. The second wave is something else. Here is the case for why systems languages are an underrated answer for the agent layer.Tue, 02 Jun 2026 00:00:00 GMThttps://tokenworm.neullabs.com/blog/c-abi-as-the-universal-ai-sdk-boundary/https://tokenworm.neullabs.com/blog/c-abi-as-the-universal-ai-sdk-boundary/tokenworm's Python, TypeScript, and Go SDKs are all thin bindings over the same Zig-compiled shared library, called through a C ABI. That choice — to make the C ABI the source of truth — is the load-bearing decision behind the whole design.Tue, 26 May 2026 00:00:00 GMThttps://tokenworm.neullabs.com/blog/why-a-960kb-binary-changes-the-ai-agent-deployment-story/https://tokenworm.neullabs.com/blog/why-a-960kb-binary-changes-the-ai-agent-deployment-story/Most AI agent SDKs ship as 200MB of language runtime plus their dependencies. tokenworm ships as a 960KB native binary that cold-starts in 8ms. That difference is not cosmetic — it changes which deployment shapes are tractable.Tue, 12 May 2026 00:00:00 GMT