the harness
UnieAI Agent Core — a better harness for open models
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.
Turns are I/O-bound — a waiting turn uses ~0 CPU, only ~3 MB of context memory.
per agent turn
CPU while waiting
cold start
* Modeling estimate, not a load test.
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
converging
Two halves of one agent-inference engine.
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.
One harness — smarter models, cheaper turns.
Decides when the model reasons, calls tools, and how a task is decomposed.
Bash, file edit, web & KB search, and any MCP server as a pluggable tool source.
Run code and tools safely — decoupled from the agent loop, not a VM per agent.
A resumable timeline ledger persists every turn for replay and observability.
Tree-based retrieval grounds answers in your knowledge base, with sources.
I/O-bound turns are multiplexed — a waiting turn uses ~0 CPU, only its context memory.
intelligence
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.
economics
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.
Build agents on a harness you can trust.