Awesome AI Agents › Documentation & Testing Assistants

truera/trulens

⭐ 3548 Python added to this list on 2025-06-22 repository created 2020-11-02

TruLens is a comprehensive tool designed for the evaluation and tracking of large language model (LLM) experiments. It provides fine-grained, stack-agnostic instrumentation and detailed evaluations to help developers systematically understand and improve the performance of their LLM applications. TruLens supports the entire development workflow by allowing users to build prototypes, connect instrumentation and logging, specify feedback functions, and run evaluations alongside their applications. This enables identification of failure modes and iterative improvement of the app. The tool emphasizes core concepts such as Feedback Functions, the RAG Triad, and Honest, Harmless, and Helpful Evaluations, which guide users in creating meaningful and actionable feedback for their models. TruLens is designed to be easy to install via PyPI and integrates smoothly into existing workflows. It offers a user-friendly interface for comparing different versions of applications and tracking their performance over time. The project encourages community involvement through contributions and provides extensive documentation and examples, including quickstart guides and Colab notebooks to help users get started quickly. TruLens is ideal for developers working with LLMs who want to move beyond simple checks and gain deeper insights into their models' behavior and effectiveness. It supports various components of LLM applications such as prompts, models, retrievers, and knowledge sources, making it a versatile tool for comprehensive evaluation and tracking.

https://github.com/truera/trulens

agent-evaluationagentopsai-agentsai-monitoringai-observabilityai-researchapp-developmentcolabcommunitydocumentationevalsexplainable-mlfailure-mode-identificationfeedback-functionsinstrumentationiterative-improvementlarge-language-modelsllm-evalllm-evaluationllmopsllmsloggingmachine-learningmodel-performanceneural-networksopen-sourceprototypingpypirag-triadtrackinguser-interface

Also in Documentation & Testing Assistants

idosal/git-mcp

GitMCP is a free, open-source remote MCP server that transforms any GitHub project into an AI-accessible documentation hub to eliminate code hallucinations and provide accurate, up-to-date project information.

steipete/agent-rules

Agent Rules is a repository of reusable rules and knowledge documents designed to improve the effectiveness of AI coding assistants like Claude Code and Cursor in software development workflows.

eli64s/readme-ai

ReadmeAI is a developer tool that automatically generates customizable README files using advanced language models and supports multiple AI providers and offline mode.

CodeBoarding/CodeBoarding

Python tool that combines static analysis with LLM reasoning to generate architecture diagrams and component documentation for a codebase, usable from a CLI, IDE extensions, a GitHub Action or CI.

samchon/nestia

Nestia is a powerful helper library suite for NestJS that enhances API development, testing, and AI chatbot integration with high performance and developer-friendly tools.

OpenBMB/RepoAgent

RepoAgent is an LLM-powered framework that automates repository-level code documentation generation to help developers quickly understand and maintain software projects.

divar-ir/ai-doc-gen

Multi-agent documentation generator from Divar that runs five concurrent analysis agents over a repository and writes a README plus CLAUDE.md, AGENTS.md and Cursor rules, with a GitLab merge-request cronjob.

Mintplex-Labs/anythingllm-docs

anythingllm-docs is a comprehensive and well-structured documentation repository for the AnythingLLM platform by Mintplex Labs, facilitating user and developer engagement through detailed guides and active maintenance.