# Unreal Agent — Unreal Labs

**URL:** <https://forum.devtalk.com/t/unreal-agent-unreal-labs/250000>\
**Category:** AI In The News\
**Tags:** via-news-bot, unreal, agent\
**Created:** [23 September 2026 03:34 UTC](https://forum.devtalk.com/t/unreal-agent-unreal-labs/250000 "2026-09-23T03:34:02Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![CommunityNews](https://forum.devtalk.com/user_avatar/forum.devtalk.com/communitynews/32/1113_2.png) [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\
**Post date:** [23 September 2026 03:34 UTC](https://forum.devtalk.com/t/unreal-agent-unreal-labs/250000/1 "2026-09-23T03:34:02Z")

</div>

> We’re sharing Unreal Agent — an agent harness that delivers up to 40% cost savings compared to Codex on production workloads and coding/science benchmarks, without any negative performance impact.

Read in full here:

> **[Unreal Agent — Unreal Labs](https://unreallabs.ai/blog/unreal-agent/)**
>
> We’re sharing Unreal Agent — an agent harness that delivers up to 40% cost savings compared to Codex on production workloads and coding/science benchmarks, without any negative performance impact.

---

<div class="post-metadata">

**Author:** ![mira\_tokarev](https://forum.devtalk.com/letter_avatar_proxy/v4/letter/m/d26b3c/32.png) [@mira\_tokarev](https://forum.devtalk.com/u/mira_tokarev)\
**Post date:** [24 September 2026 03:47 UTC](https://forum.devtalk.com/t/unreal-agent-unreal-labs/250000/2 "2026-09-24T03:47:55Z")

</div>

Interesting cost angle. A lot of harness savings come from fewer / shorter turns, but if the agent still resends a fat diary of tool logs and overlapping context every decision, the input meter keeps eating the win.

I’ve been treating that as a separate Tier-1 step: deterministic compress on the message/tool list before serialize (no extra LLM judge). Contextpress does that locally with an agent profile that keeps tool call/result pairs intact — useful when you’re already optimizing the harness.

pip install contextpress

> **[GitHub - Taha-azizi/contextpress: Deterministic context compression for LLM chat,...](https://github.com/Taha-azizi/contextpress)**
>
> Deterministic context compression for LLM chat, RAG, and agent pipelines

> **[Client Challenge](https://pypi.org/project/contextpress/)**