harbor-framework
harborHarbor is a framework for evaluating, benchmarking, and optimizing AI agents and language models across various environments and cloud providers. It...
14 repositories found
harbor-framework
harborHarbor is a framework for evaluating, benchmarking, and optimizing AI agents and language models across various environments and cloud providers. It...
future-agi
future-agiFuture AGI is an open-source platform for evaluating, tracing, and improving LLM and AI agent applications, combining evals, observability,...
ombharatiya
ai-system-design-guideA continuously updated reference guide for designing production AI systems, covering RAG architectures, LLM engineering, agentic AI, and AI...
Arize-ai
phoenixPhoenix is an AI observability and evaluation platform built for monitoring, evaluating, and debugging LLM applications and AI agents. It serves data...
mastra-ai
mastraMastra is a TypeScript framework for building AI-powered applications and agents, positioning itself as a bridge between prototyping and production....
MCPJam
inspectorMCPJam Inspector is a testing and evaluation platform designed specifically for debugging, inspecting, and evaluating MCP (Model Context Protocol)...
lmnr-ai
lmnrLaminar is an open-source observability platform purpose-built for AI agents, offering tracing, signals, evaluations, dashboards, and data annotation...
pydantic
logfirePydantic Logfire is an observability platform designed specifically for production LLM and agent systems, built by the Pydantic team. It provides...
AgentOps-AI
agentopsAgentOps is a Python SDK for monitoring, observability, and cost tracking of AI agents across multiple frameworks (CrewAI, Langchain, Autogen, OpenAI...
Kiln-AI
KilnKiln is a comprehensive workbench for the full AI development lifecycle, combining evaluations, prompt optimization, RAG, fine-tuning, synthetic data...
superlinear-ai
ragliteRAGLite is a Python toolkit for building Retrieval-Augmented Generation (RAG) systems with pluggable LLM providers, vector databases (DuckDB or...
truera
trulensTruLens is a specialized evaluation and tracking platform for LLM applications and AI agents, designed to systematically assess performance through...
GitHamza0206
simbaSimba is an open-source, production-ready customer service assistant platform built with TypeScript that emphasizes evaluation metrics and...
mattpocock
evaliteEvalite is a TypeScript-native, local-first tool for evaluating and testing LLM-powered applications. It serves developers building AI-driven...
Weekly newsletter
Every Monday: the repos worth your attention, anomaly signals and deep AI analysis. No fluff, unsubscribe any time.