YYLO Benchmark
Open-source trusted-host experiment runner for historical agent tasks, supplied coding prompts, and workflows. Runs independent attempts with retained outputs, and compares models, harnesses, and configurations with different checks or judges later. MIT licensed.
- from
- Data Science
- added
- 2026-10-10
- likes
- 0
similar
-
YYLO github.com
Open-source command-line orchestrator for coding agents and repeatable workflows, with typed task, validation, merge, and release-readiness boundaries and receipt-backed repository changes. MIT licensed, installable via npm.
-
flyology-bench github.com
Adaptive microbenchmarking with balanced comparisons, diagnostics, baselines, and machine-readable reports.
-
YYLO Ledger github.com
Command-line task and workflow ledger for coding-agent projects: stores the Kanban board and task state as hash-chained Markdown inside the repository, tracks receipts and archives, and drives typed merge and release flows across agent worktrees. MIT licensed.
-
OpenLIT github.com
Open-source GenAI and LLM observability platform native to OpenTelemetry with traces and metrics. #opensource
-
Opik github.com
An open-source platform for tracing, evaluating, and monitoring LLM applications. #opensource
-
Yolov5 github.com
Data Science › Agents > Tools: “Open-source trusted-host experiment runner for historical agent tasks, supplied coding prompts, and workflows. Runs independent attempts with retained outputs, and compares models, harnesses, and configurations with different checks or judges later. MIT licensed.”