#Evals

Showing 28 of 28 repositories tagged #evals, ranked by stars

mastra-ai
mastra-ai
mastra

Mastra is the modern TypeScript framework for AI-powered applications and agents.

Score
100
★ 26.0k ⑂ 2.4k +24/day
TypeScript
Arize-ai
Arize-ai
phoenix

AI Observability & Evaluation

Score
100
★ 10.5k ⑂ 974 +5/day
Python
AgentOps-AI
AgentOps-AI
agentops

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

Score
75
★ 5.7k ⑂ 604 +4/day
Python
Kiln-AI
Kiln-AI
Kiln

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

Score
50
★ 5.0k ⑂ 377 +2/day
Python
pydantic
pydantic
logfire

AI observability platform for production LLM and agent systems.

Score
0
★ 4.4k ⑂ 253 +18/day
Python
truera
truera
trulens

Evaluation and Tracking for LLM Experiments and AI Agents

Score
0
★ 3.4k ⑂ 309 +16/day
Python
lmnr-ai
lmnr-ai
lmnr

Laminar - open-source observability platform purpose-built for AI agents. YC S24.

Score
0
★ 3.1k ⑂ 216 +5/day
TypeScript
harbor-framework
harbor-framework
harbor

Harbor is a framework for running agent evaluations and creating and using RL environments.

Score
25
★ 3.0k ⑂ 1.3k +29/day
Python
ombharatiya
ombharatiya
ai-system-design-guide

AI system design guide for engineers building production AI systems and evals.

Score
100
★ 2.1k ⑂ 444 +65/day
MCPJam
MCPJam
inspector

Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.

Score
92
★ 2.1k ⑂ 244 +8/day
TypeScript
mattpocock
mattpocock
evalite

Evaluate your LLM-powered apps with TypeScript

Score
0
★ 1.6k ⑂ 95 +4/day
TypeScript
GitHamza0206
GitHamza0206
simba

OpenSource Production ready Customer service with built in Evals and monitoring

Score
75
★ 1.5k ⑂ 106
TypeScript
future-agi
future-agi
future-agi

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

Score
83
★ 1.3k ⑂ 350 +7/day
Python
superlinear-ai
superlinear-ai
raglite

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

Score
67
★ 1.2k ⑂ 108 +1/day
Python
benchflow-ai
benchflow-ai
awesome-evals

A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.

Score
58
★ 694 ⑂ 50 +30/day
heymrun
heymrun
heym

Build AI workflows by prompt or visual canvas. Heym is source-available and self-hosted, with agents, RAG, MCP, HITL, observability, evals, token cost tracking and more.

Score
100
★ 691 ⑂ 69 +16/day
Python
microsoft
microsoft
promptpex

Test Generation for Prompts

Score
50
★ 162 ⑂ 19
TeX
zapier
zapier
AutomationBench

A benchmark for evaluating AI agents on realistic business workflows

Score
42
★ 115 ⑂ 10 +11/day
Python
vstorm-co
vstorm-co
awesome-pydantic-ai

An opinionated list of awesome Pydantic-AI frameworks, libraries, software and resources.

Score
25
★ 86 ⑂ 15 +3/day
spences10
spences10
my-pi

Composable pi coding agent with MCP, LSP, agent chains, prompt presets, and local eval telemetry

Score
67
★ 80 ⑂ 12 +6/day
TypeScript
ahmedEid1
ahmedEid1
lumen

Lumen — learner-owned AI education platform. Tell the AI what you want to learn: it builds you a private course in ~a minute, tutors you with course-scoped RAG + citations, and lets you share, clone & remix via a moderated catalog. BYOK, custom no-LangChain multi-agent orchestrator, golden evals in CI, MCP server. Live demo + public /eval.

Score
33
★ 74 ⑂ 37
Python
voratiq
voratiq
voratiq

Which coding agent wins on real work?

Score
0
★ 73 ⑂ 2
TypeScript
fastxyz
fastxyz
skill-optimizer

Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs

Score
33
★ 70 ⑂ 11 +1/day
TypeScript
mamgad
mamgad
DVBLab

This course uses a deliberately vulnerable banking application to demonstrate common security vulnerabilities, their impact, and how to fix them. The application is built with Flask (backend) and React (frontend).

Score
0
★ 59 ⑂ 9 +1/day
Python
AIAnytime
AIAnytime
rag-evaluator

A library for evaluating Retrieval-Augmented Generation (RAG) systems (The traditional ways).

Score
8
★ 45 ⑂ 19 +1/day
Python
NirantK
NirantK
rag-to-riches
Score
0
★ 29 ⑂ 7
Jupyter Notebook
sutro-sh
sutro-sh
sutro

Analyze and generate unstructured data using LLMs, from quick experiments to billion token jobs.

Score
0
★ 17 ⑂ 2
Python
Moai-Team-LLC
Moai-Team-LLC
agentic-product-standard

The canonical standard for building production-grade agentic products — autonomy ladder, composition patterns, the 7-layer harness, eval discipline — plus a Claude Code skill set that operationalizes it.

Score
17
★ 13 ⑂ 0
Shell
Related Topics
#llm#ai#mcp#rag#typescript#llm-evaluation#openai#evaluation#python#observability#ai-agents#agents

© 2026 GitRepoTrend · GitHub repositories by topic · Updated weekly