Alternatives to TablePlus

AI agent observability for tracing, monitoring, and evaluating LLM apps

Open-source MCP server for live Chrome browser control and DevTools debugging

OpenTelemetry-native observability with autonomous AI agents

Managed vector database for AI agent memory and retrieval

Open-source LLM observability and prompt management for production AI agents.

Generate & deploy Next.js landing pages in 5 minutes with AI.

Open-source inference framework for 1-bit LLMs on CPU and GPU.

Fast web crawling, scraping & search API for AI agents

Open-source AI observability for LLM agent tracing and evaluation.

Co-own and monetize AI agents with on-chain ownership and staking rewards.

Open-source observability and evaluation for AI agents

AI agents that handle on-call and production operations so engineers can build.

Enterprise AI platform with 40+ pre-built applications for rapid deployment

Python decorator library for minimal-abstraction LLM apps with observability

Build and deploy full-stack apps from natural language with Replit Agent.

Chinese LLM platform for enterprise agents, MaaS, and open-source models

Docs, SDKs, and CLI from one API spec, built for the AI era

Build full-stack web apps by chatting with AI.

Build full-stack React/Next.js apps from plain English and deploy instantly

Sovereign domain-specific SLLMs for European enterprises & government.

Eval engineering platform that turns evals into production guardrails at 96% lower cost.

Turn ideas into live apps and websites with AI, no coding required.

Automated NAS and inference optimization for NVIDIA hardware.

Unified API lifecycle platform with AI-powered testing and documentation

Opik observability, evaluation, and auto-fix for AI agents with cost intelligence

Open-source OpenTelemetry LLM observability for Python devs

Unify LLM evaluation, observability, and red teaming in one shared workspace.

Open source AI engineering platform for agents, LLMs, and models.

End-to-end ML and AI platform for building, training, and deploying models on AWS.

Run open-source LLMs locally with one command, scale to cloud when needed.