Help developers discover the tools you use. Get visibility for your team's tech choices and contribute to the community's knowledge.
It is the toolkit for evaluating and developing robust and reliable AI agents. Build compliant virtual employees with observability, evals, and replay analytics. No more black boxes and prompt guessing. | It is a no-code compute platform for language models. It is aimed at AI developers and product builders. You can also vibe-check and compare quality, performance, and cost at once across a wide selection of open-source and proprietary LLMs. |
Agent agnostic SDK;
LLM cost (OpenAI, etc);
Replay analytics;
Analytics dashboard;
Public model testing | Query and compare a large selection of open-source and proprietary models at once;
Replace costly APIs with cheap custom AI models;
Airtrain’s LLM-assisted scoring simplifies model grading using your task descriptions;
Cut your AI costs by up to 90% |
Statistics | |
GitHub Stars 5.0K | GitHub Stars - |
GitHub Forks 488 | GitHub Forks - |
Stacks 0 | Stacks 0 |
Followers 0 | Followers 2 |
Votes 0 | Votes 0 |
Integrations | |

It is a cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, it empowers agents to work together seamlessly, tackling complex tasks.

It is a platform for building production-grade LLM applications. It lets you debug, test, evaluate, and monitor chains and intelligent agents built on any LLM framework and seamlessly integrates with LangChain, the go-to open source framework for building with LLMs.

Is an all-in-one AI coding platform that allows you build apps and websites by chatting with AI. YouWare enables full-stack code generation and deployment with a shareable URL instantly. no code, no setup, no hassle.

The collaborative testing platform for LLM applications and agents. Your whole team defines quality requirements together, Rhesis generates thousands of test scenarios covering edge cases, simulates realistic multi-turn conversations, and delivers actionable reviews. Testing infrastructure built for Gen AI.

A frontier coding agent engineered to maximize what's possible with today's latest models—autonomous reasoning, comprehensive code editing, and complex task execution.

Vivgrid is an AI agent infrastructure platform that helps developers and startups build, observe, evaluate, and deploy AI agents with safety guardrails and global low-latency inference. Support for GPT-5, Gemini 2.5 Pro, and DeepSeek-V3. Start free with $200 monthly credits. Ship production-ready AI agents confidently.

Ainisa is the agentic AI platform that actually works: Train agents on your data (products/FAQs/orders), deploy to WhatsApp, Telegram, or website in minutes, and let them take real actions—book meetings, trigger n8n/Zapier, fetch Stripe orders, fill forms, close deals. Bring your own OpenAI/Claude key for zero hidden costs. No markups, no hallucinations. Launch special: First 100 sign-ups get 20% off for 3 months. 4 ready templates: General, Customer Support, E-commerce, Lead Gen. Perfect for e-com stores, agencies, and solo founders. Start free (200 messages/50 chats/mo).

Home Download Features Pricing Marketplace Support DiscoverVibe Web Scraping & Vibe Ai Automation For Agencies & Enterprises Build Ai powered Automation Infrastructure & deploy it as Agentic Software, SaaS or DataSets Strategic Partners OS Compatibility Browser Compatibility Demos of how to create &

AI-driven helpdesk software that simplifies ticketing, auto-resolves 60% of customer queries, and helps teams deliver fast, efficient customer support.

Is a training API for researchers and developers.