A simple-to-use, open-source LLM evaluation framework, specialized for unit testing LLM apps.

Are you the maintainer?
Claim this page →Deepeval
A simple-to-use, open-source LLM evaluation framework, specialized for unit testing LLM apps.
01 / About
About Deepeval.
02 / Credibility
Derived from GitHub, not voted.
Public-signal score, discounted for bought-star and bot-stargazer patterns — not a user rating. How scores are calculated.
GitHub credibility score
- ✓ Contributors & bus-factor — 18 recent contributors
- ✓ Commit recency — last commit 2d ago
- ✓ Commit cadence — 620 commits in 90 days
- ✓ Issue close ratio — 68% of issues closed
- ✓ Release cadence — 7 releases in 12 months
- ✓ Stars (log-damped) — 16,821 stars (log-damped)
- ✓ Star authenticity — organic star growth — no velocity anomaly
- ✓ Engagement-to-star ratio — healthy engagement (0.27 per star)
03 / Discussion CREDIBILITY-GATED
Discussion · 0
Reading is open to everyone. Only verified humans or builders at GitHub B+ can post or vote — every comment carries its author's credibility.
- No comments yet — be the first to start the discussion.
04 / Related
More to explore.
ToolVoltagent
VoltAgent
AI Agent Engineering Platform
ToolAgent Skills
WordPress
Expert-level WordPress knowledge for AI coding assistants - blocks, themes, plugins, and best practices
ToolClaude Code
anthropics
agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
ToolContext7
upstash
ToolEngram
Gentleman-Programming
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
ToolFastmcp
PrefectHQ
The fast, Pythonic way to build MCP servers and clients. Declare a tool with a Python function, and the schema, validation, and documentation are generated automatically.
05 / Build
Build with Deepeval.
Browse the catalogue for frameworks, tools, and blueprints — each scored on real GitHub credibility.
Browse the catalogue