Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915934040489984 |
|---|---|
| author | Wang, Huacan Zhou, Jie Zhu, Ningyan Zhang, Shuo Chen, Feiyu Wu, Jiarou Chen, Ge Liu, Chen Chen, Wangyi Mou, Xiaofeng Xu, Yi |
| author_facet | Wang, Huacan Zhou, Jie Zhu, Ningyan Zhang, Shuo Chen, Feiyu Wu, Jiarou Chen, Ge Liu, Chen Chen, Wangyi Mou, Xiaofeng Xu, Yi |
| contents | AI coding agents have become central to developer workflows, yet every existing solution locks its reasoning capabilities within a specific delivery form, such as a CLI, IDE plugin, or web application. This limitation creates systemic barriers when enterprises attempt to reuse these capabilities across heterogeneous engineering environments. To address this challenge, we present Sema Code, an open AI coding framework built on the principle of being embeddable, pluggable, and framework-first. Sema Code completely decouples the core agent engine from all client layers, publishing it as a standalone npm library that any runtime can drive programmatically. Built around this architecture, we designed eight key mechanisms: multi-tenant engine isolation, FIFO input queuing with safe session reconstruction, adaptive context compression, multi-agent collaborative scheduling, intelligent Todo-based process management, four-layer asynchronous permission control, three-tier ecosystem integration spanning MCP, Skills, and Plugins, and a background task framework with separated execution and observation privileges. These mechanisms collectively address the engineering challenges of transforming a complex agent engine into a shared, programmable core. Demonstrating its architectural versatility, the same Sema Core engine simultaneously powers a VSCode extension and a multi-channel messaging gateway, which we name SemaClaw, to unify agent interactions across platforms such as Telegram and Feishu. These represent two fundamentally different product forms sharing an identical reasoning kernel, differing only at the client layer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11045 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure Wang, Huacan Zhou, Jie Zhu, Ningyan Zhang, Shuo Chen, Feiyu Wu, Jiarou Chen, Ge Liu, Chen Chen, Wangyi Mou, Xiaofeng Xu, Yi Software Engineering AI coding agents have become central to developer workflows, yet every existing solution locks its reasoning capabilities within a specific delivery form, such as a CLI, IDE plugin, or web application. This limitation creates systemic barriers when enterprises attempt to reuse these capabilities across heterogeneous engineering environments. To address this challenge, we present Sema Code, an open AI coding framework built on the principle of being embeddable, pluggable, and framework-first. Sema Code completely decouples the core agent engine from all client layers, publishing it as a standalone npm library that any runtime can drive programmatically. Built around this architecture, we designed eight key mechanisms: multi-tenant engine isolation, FIFO input queuing with safe session reconstruction, adaptive context compression, multi-agent collaborative scheduling, intelligent Todo-based process management, four-layer asynchronous permission control, three-tier ecosystem integration spanning MCP, Skills, and Plugins, and a background task framework with separated execution and observation privileges. These mechanisms collectively address the engineering challenges of transforming a complex agent engine into a shared, programmable core. Demonstrating its architectural versatility, the same Sema Core engine simultaneously powers a VSCode extension and a multi-channel messaging gateway, which we name SemaClaw, to unify agent interactions across platforms such as Telegram and Feishu. These represent two fundamentally different product forms sharing an identical reasoning kernel, differing only at the client layer. |
| title | Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2604.11045 |