OpenRouter Model Fusion
OpenRouter Fusion turns a prompt into a small multi-model deliberation, making combined model results as easy to call as a single model. A panel of expert models analyzes the prompt in parallel with web search and web fetch enabled, then a judge model compares their responses and returns structured analysis that includes consensus, contradictions, partial coverage, unique insights, and blind spots. The final answer is written from that analysis, helping users benefit from multiple perspectives rather than relying on one model alone. Fusion is built for cases where a single model is not enough, such as research, expert critique, compare-and-contrast prompts, multi-domain questions, or any task where being wrong is expensive. Users can call Fusion directly through the openrouter/fusion model alias, enable it as the fusion server tool, or configure it through the Fusion plugin; all three entry points use the same pipeline.
Learn more
ChainForge
ChainForge is an open-source visual programming environment designed for prompt engineering and large language model evaluation. It enables users to assess the robustness of prompts and text-generation models beyond anecdotal evidence. Simultaneously test prompt ideas and variations across multiple LLMs to identify the most effective combinations. Evaluate response quality across different prompts, models, and settings to select the optimal configuration for specific use cases. Set up evaluation metrics and visualize results across prompts, parameters, models, and settings, facilitating data-driven decision-making. Manage multiple conversations simultaneously, template follow-up messages, and inspect outputs at each turn to refine interactions. ChainForge supports various model providers, including OpenAI, HuggingFace, Anthropic, Google PaLM2, Azure OpenAI endpoints, and locally hosted models like Alpaca and Llama. Users can adjust model settings and utilize visualization nodes.
Learn more
DeepEval
DeepEval is a simple-to-use, open source LLM evaluation framework, for evaluating and testing large-language model systems. It is similar to Pytest but specialized for unit testing LLM outputs. DeepEval incorporates the latest research to evaluate LLM outputs based on metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., which uses LLMs and various other NLP models that run locally on your machine for evaluation. Whether your application is implemented via RAG or fine-tuning, LangChain, or LlamaIndex, DeepEval has you covered. With it, you can easily determine the optimal hyperparameters to improve your RAG pipeline, prevent prompt drifting, or even transition from OpenAI to hosting your own Llama2 with confidence. The framework supports synthetic dataset generation with advanced evolution techniques and integrates seamlessly with popular frameworks, allowing for efficient benchmarking and optimization of LLM systems.
Learn more
Selene 1
Atla's Selene 1 API offers state-of-the-art AI evaluation models, enabling developers to define custom evaluation criteria and obtain precise judgments on their AI applications' performance. Selene outperforms frontier models on commonly used evaluation benchmarks, ensuring accurate and reliable assessments. Users can customize evaluations to their specific use cases through the Alignment Platform, allowing for fine-grained analysis and tailored scoring formats. The API provides actionable critiques alongside accurate evaluation scores, facilitating seamless integration into existing workflows. Pre-built metrics, such as relevance, correctness, helpfulness, faithfulness, logical coherence, and conciseness, are available to address common evaluation scenarios, including detecting hallucinations in retrieval-augmented generation applications or comparing outputs to ground truth data.
Learn more
