HarnessX · Darwin-Agent

confidence: mediumbeta222

A research-grade 'harness foundry' (MIT, v0.1.0 beta, arXiv paper 2606.14249) that composes agent harnesses from typed reusable processors across seven categories (context, control, evaluation, memory, multi-model, observability, tools) and evolves them via the AEGIS trace-driven engine, reporting an average +14.5% gain across ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified without touching model weights.

Homepagehttps://github.com/Darwin-Agent/HarnessX
Repositoryhttps://github.com/Darwin-Agent/HarnessX
Licenseopen-source
Domainresearch
Form factorsdk
Model-agnostic✓ yes
Native models
Local models? unknown
Pricingbyok
MCP client? unknown
Agent Skills support? unknown
Plugins / hooks✓ yes
Sandboxingoptional
Autonomy spectrumsemi-autonomous → autonomous-local
Subagents? unknown
Parallel sessions? unknown
Context managementcompaction · persistent-memory
Headless / API✓ yes
GitHub integration? unknown
Sources

✓ profile last verified 2026-07-08 · benchmark figures are vendor-reported unless a source states otherwise