bytedance/deer-flow
DeerFlow is a community-driven deep research framework that integrates language models with web search, crawling, and Python execution tools to facilitate comprehensive AI-powered research workflows.
Awesome AI Agents › Reasoning Frameworks
SalesforceAIResearch/xLAM
xLAM is a cutting-edge project developed by Salesforce AI Research that introduces a family of Large Action Models designed to empower AI agent systems. The project addresses the challenges faced by autonomous agents powered by large language models (LLMs) in handling heterogeneous data sources with multi-turn trajectories. xLAM aggregates agent trajectories from diverse environments and scenarios, standardizing and unifying them into a consistent format. This unification facilitates the creation of a generic data loader optimized for agent training, ensuring balanced training across different data sources and maintaining independent randomness during dataset partitioning and model training. The repository provides a comprehensive suite of models ranging from smaller "tiny giant" models to industrial-scale powerhouses, all optimized for multi-turn conversation and function-calling tasks. These models have achieved top rankings on the Berkeley Function-Calling Leaderboard, demonstrating their superior performance compared to many larger models. The project also offers extensive resources including model instructions, training pipelines, benchmarks, and installation guides. xLAM supports a wide context length, with some models capable of handling up to 128k tokens, making them suitable for complex and extended interactions. The project is actively maintained with frequent updates, open-source releases, and a supportive community on Discord. It also emphasizes research transparency by partially releasing data related to xLAM to advance the agent research community. Overall, xLAM represents a significant advancement in the development of AI agents, providing powerful tools and models that enhance the capabilities of autonomous systems in understanding and executing complex actions through natural language interactions.
https://github.com/SalesforceAIResearch/xLAM
Also in Reasoning Frameworks
VectifyAI/PageIndex
PageIndex is a reasoning-based document indexing and retrieval system that uses a hierarchical tree structure to enable human-like, vectorless retrieval and multi-step reasoning over long professional documents.
guidance-ai/guidance
Guidance is a programming paradigm and library that enables efficient and fine-grained control over large language models to produce structured, high-quality outputs with reduced latency and cost.
friuns2/BlackFriday-GPTs-Prompts
A curated repository of free GPT prompts and jailbreaks across various domains, enabling users to utilize GPT models without a subscription to GPT Plus.
refly-ai/refly
Refly is an open-source AI-native creation engine that combines multi-threaded dialogues, multimodal inputs, knowledge base integration, and AI-powered tools to transform ideas into production-ready interactive content and web applications.
mongodb-developer/GenAI-Showcase
MongoDB's GenAI Showcase is a comprehensive repository offering examples and applications that integrate MongoDB with advanced Generative AI techniques like Retrieval-Augmented Generation and AI Agents to support AI development and innovation.
anysphere/priompt
Priompt is a JSX-based prompting library that uses a priority system to efficiently construct token-limited prompts for language models, inspired by React's component design.
HKUDS/Auto-Deep-Research
Auto-Deep-Research is an open-source, fully automated, and cost-effective personal AI assistant that supports multiple large language models and offers a one-click launch experience as an alternative to OpenAI's Deep Research.