Agentic API adds a stateful layer in front of vLLM for open-model agent runtimes
techNmak · x · 2026-09-03
Agentic API is a stateful API layer in front of vLLM that turns raw inference into an agent runtime: session state, tool-call loops, streaming, and persistence move server-side, so clients resume via previousresponseid instead of resending full context. Tools are split into gateway-owned (web search, MCP, server-side), client-owned (Codex shell, editor actions), and provider-owned (passthrough), giving open models on vLLM an OpenAI-style stateful agent API.
More from coding & agent
- Muse Spark 1.3 released with focus on instruction following and long-horizon coding — armand_ruiz · 2026-09-03
- GitHub decodes the new AI dev lingo: loop engineering, harnesses, squads and hill climbing — GitHub Blog AI/ML · 2026-09-03
- Reef: open-source infra that lets agents keep evolving weights and harness after deployment — Scobleizer · 2026-09-03
- Self-Hosted Agent Memory Failed Silently: Writes Fine, Retrieval Dead, No Errors — eldrugo85 · 2026-09-03
- Thoughtworks CTO: maybe we shouldn't be reviewing all this code anymore — rseroter · 2026-09-03
- moyix says XBOW can also pull off full-chain autonomous pentesting — moyix · 2026-09-03