Medley Launches Mission Harness: Contract-Driven DAG + Self-Improving Meta-Harness Sets New Highs Across Benchmarks
ycombinator · x · 2026-07-30
Spine AI team releases Medley, a framework built on the idea that 'the harness is the capability multiplier.' It comprises two systems:
- /mission: For Claude Code and Codex, turns ambitious goals into durable contracts, adaptive task graphs, routed workers, and role-separated acceptance stages.
- Medley Bench: A benchmark-specialized architecture where an unsupervised meta-harness learns benchmark-specific instructions by selecting tasks, analyzing execution traces, and editing planning, worker, acceptance, and runtime skills.
The framework achieves new reported highs across terminal work, clinician conversations, full-stack applications, and drug discovery. Learned procedures transfer across closed and open-weight models without changing model weights.
More from coding & agent
- Railcode Launches: A Secure Environment for Internal AI Agents — julianweisser · 2026-07-30
- ComfyUI-Agnes-AI Update: Native Settings Panel & Up to 18s Video Generation — Narrow-Particular202 · 2026-07-30
- Cognition Lab Talk: RL and Inference Optimization Are Converging — AAAzzam · 2026-07-30
- Open-Sourcing ravendr: A Voice Research Agent with Inspectable Multi-Step Workflows — ojus_render · 2026-07-30
- Understanding is the New Bottleneck: 7-Step Review for AI Coding — MaryamMiradi · 2026-07-30
- Developer Builds Calendar Agent Using Private Wiki and Custom CLI — mattpocockuk · 2026-07-30