Are you the maintainer?
Claim this page →A framework for A/B testing of prompts, models, and tools within agent workflows.
01 / About
Agenta is a framework for A/B testing of prompts, models, and tools within agent workflows. It lets you evaluate and compare different agent configurations side by side.
When comparing agent configurations or conducting A/B tests, Agenta facilitates structured evaluations.
02 / Credibility
Public-signal score, discounted for bought-star and bot-stargazer patterns — not a user rating. How scores are calculated.
Score unavailable
We haven't been able to compute a GitHub credibility score for this tool yet. It'll appear here once the evaluator runs.
03 / Discussion CREDIBILITY-GATED
Reading is open to everyone. Only verified humans or builders at GitHub B+ can post or rate — every comment carries its author's credibility.
04 / Related
ToolControl browsers programmatically with LLM agents through a high-level, LLM-friendly API.
ToolJuliusBrussee
An experimental LoRA fine-tune of Gemma to speak caveman-mode natively.
ToolJuliusBrussee
A TypeScript implementation of the caveman compression engine.
Toolegorfedorov
Tracks token usage, blocks redundant reads, and supports .contextignore and budget alerts.
ToolNodeNestor
A proxy plugin that rolls context compression past 100K tokens.
Toolnadimtuhin
Restructures CLAUDE.md and docs for roughly 90% token savings with a CLI audit and compress.
05 / Build
Browse the catalogue for harnesses, tools, and blueprints — each scored on real GitHub credibility.
Browse the catalogue