Agent Core is the harness that makes open models smarter and the runtime that makes them cheap to run. It decouples session, sandbox, filesystem, orchestration and tools into efficient services — so hundreds of agents run in one process, not dozens of VMs.
Agent run
Analyze last quarter's complaints by product line
Same model — AIME 78.3% → 97.2%
AIME 2025 uplift on MiniMax-M2 (78.3% → 97.2%) with Agent Core 2
Concurrent agent turns per replica vs. ~10–40 for sandbox-per-agent*
Memory per agent turn — ~0 CPU while waiting on model & tools*
Cold start — stateless, linear horizontal scaling
The same open model gets materially stronger and more reliable when it runs inside a purpose-built harness — better planning, better tool use, stable loops.
UnieAI Agent Core
Decoupled, async agent runtime — hundreds of concurrent turns per process, single-digit MB each.
UnieInfra
Token-efficient throughput density and low TTFT for agent inference. Converging with Agent Core into one engine.
Agent Core 1.0 — a production-grade native function-calling agent loop, hardened inside UnieAI Studio. Zero runtime dependencies.
One iteration, one model step, driven by native tool_calls; results re-enter message history. Bounded concurrency, per-tool timeouts, and automatic repair of malformed calls.
Doom-loop guards (identical calls, same-tool streaks), transient-error retry with backoff, context-overflow recovery — and a soft-landing wrap-up that guarantees a text answer at the step budget.
Zero-LLM compaction at entry plus mid-loop pruning of old tool outputs — long runs stay inside the window, with no compaction pause.
The model edits its own Tier-1 core memory via a memory tool (char-capped buckets, threat-scanned writes); a background review agent reflects after replies.
load_skill injects skill bodies only when needed, keeping the base context small.
A task tool forks an isolated child loop and returns only a distilled conclusion to the parent.
The core ships only generic tools (todo / memory / skill / task); your domain tools — search, SQL, APIs, GPU kernels — are injected as domainToolBuilders. Two production consumers prove the seam: UnieAI Studio injects kb, sql, bi, api and mcp; Kernel-Design-Agent injects CUDA-kernel tools. Zero runtime dependencies.
Traditional frameworks give every agent its own sandbox: hundreds of MB to GB each, seconds to cold-start, so high concurrency means spinning up hundreds of VMs. Agent Core decouples the agent into efficient services and multiplexes I/O-bound turns in a single process.