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
letta-ai/letta
Letta, formerly known as MemGPT, is an open-source framework designed for building stateful large language model (LLM) applications. It enables the creation of stateful agents that possess advanced reasoning capabilities, transparent long-term memory, and context management. The framework is model-agnostic and white-box, allowing developers to build and run intelligent agents that maintain memory and reasoning over time. Letta agents operate inside the Letta server, which persists agent data to a database, and can be interacted with via REST API, Python and TypeScript SDKs, or through a graphical interface called the Agent Development Environment (ADE). The Letta server supports integration with various LLM API backends such as OpenAI, Anthropic, vLLM, and Ollama, making it flexible for different AI model providers. The recommended deployment method is via Docker, with environment variables used to configure API keys and data persistence. The ADE provides a user-friendly graphical interface for creating, deploying, interacting with, and observing Letta agents, useful for testing, debugging, and managing agents in production or development environments. Letta emphasizes transparency and control, offering a white-box approach to agent development. It supports long-term memory and reasoning, which are critical for building sophisticated AI applications that require context retention and complex decision-making. The project also provides extensive documentation, a community Discord, and a cloud service for early access. It is licensed under Apache 2.0 and actively maintained with regular releases and Docker images available. In summary, Letta is a comprehensive framework for developing stateful AI agents with memory and reasoning, supporting multiple LLM backends, and providing tools for both developers and end-users to manage and interact with these agents effectively.
https://github.com/letta-ai/letta
Also in End-to-End Optimizers
topoteretes/cognee
Cognee is an open-source project that provides scalable and modular memory solutions for AI agents using ECL pipelines, enabling efficient data ingestion, knowledge graph generation, and query capabilities to enhance AI performance and reduce hallucinations.
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.