“prompting”

Task-based NLP engine for structured outputs from LLMs

⚡ Vigil ⚡ Security scanner for detecting prompt injections, jailbreaks, and risky Large Language Model inputs

The Security Toolkit for LLM Interactions

Unified platform to evaluate and improve Generative AI applications

Prompt. Generate Synthetic Data. Train & Align Models.

Context compression layer for AI agents

Multi-harness agentic plugin marketplace

Simple, Explicit and Transparent LLM Applications

The open source AI engineering platform for agents, LLMs, and ML models

Comprehensive tracing, automated evaluations, and production-ready dashboards for LLM applications.

AI Observability & Evaluation

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

OptiLLM is an OpenAI API-compatible optimizing inference proxy that enhances LLM accuracy and performance on reasoning tasks without needing to train or fine-tune models.

Automatic Differentiation via Text

Generalist and Lightweight Model for Named Entity Recognition

Open-source document intelligence platform for building on unstructured data.

World's first open-source, agentic video production system.

The absolute trainer to light up AI agents.

CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents.

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework

🤖 Self-modifying Framework from the Future 🔮 World's First AMS