Keyword: meta-harness
- agentic-flowReleased4d agoVersion2.1.0
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
- @metaharness/darwinReleased5d agoVersion0.7.0
Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench Lite code-repair — 7.7% open-loop -> 58.3% via cheap->frontier tiering (official swebench Docker, verified), ~$0.01-$0.74/instance vs $1-20 for frontier agents; (2) Darwin Shie
- metaharnessReleased6d agoVersion0.2.6
MetaHarness — mint a custom AI agent harness from any repo. Browser Studio + npx metaharness CLI. Runs on Claude Code, Codex, pi.dev, Hermes, OpenClaw, RVM.
- @beyland/piperReleased7h agoVersion0.1.0
A meta-harness for designing durable loops that prompt coding agents
- @metaharness/jujutsuReleased16h agoVersion0.2.0
Lock-free version-control-for-agents capability for MetaHarness. Wraps agentic-jujutsu (jj/Jujutsu op-log, QuantumDAG agent coordination, ReasoningBank trajectories, ML-DSA signing) as a removable augmentation, and bridges it to agenticow COW memory branc