headroomlabs-ai/headroom
Headroom is a context compression layer for AI agents, reducing token usage by 60-95% across tool outputs, logs, RAG chunks, files, and conversation history, while maintaining accuracy.
Awesome AI Agents › End-to-End Optimizers
topoteretes/cognee
Cognee is an innovative open-source project designed to provide memory capabilities for AI agents with minimal code complexity, enabling developers to build dynamic agent memory systems using scalable and modular ECL (Extract, Cognify, Load) pipelines. The project focuses on interconnecting and retrieving past conversations, documents, images, and audio transcriptions to enhance AI agent performance by reducing hallucinations, developer effort, and operational costs. Cognee supports loading data into graph and vector databases using Pydantic, facilitating seamless data manipulation from over 30 different data sources during ingestion. The project offers a straightforward setup process, including a Google Colab notebook and a starter repository to help users get started quickly. It supports integration with various large language model (LLM) providers, with environment variable configuration for API keys. The core functionality includes adding textual data, generating knowledge graphs, and querying these graphs to retrieve relevant information, demonstrated through simple Python asynchronous code examples. Cognee's architecture is visually represented to explain its concept and workflow, emphasizing its modular and scalable design. The project also provides demos showcasing AI memory concepts, GraphRAG integration, and compatibility with local models like Ollama. It encourages community contributions and maintains a code of conduct to foster a respectful and enjoyable open-source environment. With features like graph visualization, extensive documentation, and active community engagement through Discord and GitHub, Cognee stands out as a powerful tool for developers looking to implement advanced memory functionalities in AI agents efficiently. Its focus on reducing hallucinations and cost while supporting diverse data sources makes it a valuable asset in the AI development ecosystem.
https://github.com/topoteretes/cognee
Also in End-to-End Optimizers
letta-ai/letta
Letta is an open-source framework for building stateful AI agents with advanced reasoning, transparent long-term memory, and context management, supporting multiple LLM backends and providing a graphical development environment.
langchain-ai/opengpts
OpenGPTs is an open-source platform that replicates and extends OpenAI's GPTs and Assistants API, offering customizable cognitive architectures, extensive tooling, and support for multiple language models and vector databases.
aiwaves-cn/agents
Agents 2.0 is an open-source framework that enables the training and self-evolution of autonomous language agents through symbolic learning inspired by neural network methodologies.
getzep/zep
Zep is an AI memory foundation that uses a temporal Knowledge Graph to enable continuous learning and personalized experiences for AI agents by efficiently managing and retrieving contextual chat and data artifacts.
algorithmicsuperintelligence/optillm
OptiLLM is an optimizing inference proxy that significantly improves the accuracy and performance of large language models on reasoning tasks without requiring any model training, by applying over 20 advanced optimization techniques during inference.
mll-lab-nu/RAGEN
A reinforcement learning framework for training multi-turn reasoning LLM agents on the StarPO algorithm, shipping ten Gym-compatible environments plus diagnostics for echo-trap and reasoning-collapse failure modes.
langfengQ/verl-agent
verl-agent is an extension of veRL designed for scalable training of large language and vision-language model agents via reinforcement learning, featuring customizable input structures, diverse RL algorithms including GiGPO, and support for multi-modal environments.