AgentDish directory
evaluation harness
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
#814
↓ -6
Mnemiq
Open-source text-to-SQL engine tuned to your own database, with configurable pipeline stages, policy checks, and an evaluation harness for measuring performance on real schemas. |
Developer Tools / Code Assistant | 84 | ↓ -6 | 2 days ago | Details |
A technical case study on reducing token usage in a coding agent, including a model-free harness, wire-level measurement, and several concrete optimizations that cut a long run from 1.04M to 517k tokens. |
AI blog / engineering write-up / Agent optimization | 78 | ↑ +6 | 35 days ago | Details |