Strands Agents

All projects

Agents / Skills

An open-source autonomous agent harness SDK optimized for frontier benchmarks.

byAlbert Zhao & Chen Wu

PlayableOpen source

Strands Agents media is blocked

Allow external media to connect to the provider and play this content.

Description

An agent SDK and loop harness that enables models to solve complex reasoning tasks via token-efficient context engineering and iterative tool use. By managing environment state in external logs rather than vision-only harnesses, it allowed a model to achieve a near-perfect 99.95% score on the ARC-AGI-3 intelligence benchmark using shell and Python script execution.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: Achieving 99.95% on ARC-AGI-3 is a landmark result for AI agents, proving the power of well-constructed tool loops.
Attributed to: Albert Zhao & Chen Wu@strands-agents
Built with: GPT-6 Astra Opus 5 Opus 4.8 GPT-5.5 Pro GPT Image 2 Opus 4.7 LTX 2.3 Pro 3.1 Pro Opus 4.6 Vidu Q3 Pro Seedream 5.0 Pro Seedance 1.5 Pro Flux 2 Pro Opus 4.5 Nano Banana Pro Gemini 3 Pro Gemini 2.5 Pro
Links: strandsagents.com
View tweet
View GitHub repo
Tags: #sdk #benchmark #arc-agi #reasoning

Discovered: X
First posted: X · Sep 4, 2026
Listed: Added 11d ago
Build: Strong
Models: Strong

Strands Agents

Description

Timeline

Strands Agents

Description

Timeline