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
langchain-ai/opengpts
OpenGPTs is an open-source project designed to replicate and extend the experience of OpenAI's GPTs and Assistants API. It is built on top of LangGraph, a framework for creating agent runtimes, and integrates with LangChain, LangServe, and LangSmith to provide a comprehensive platform for building AI-powered assistants and chatbots. The project offers extensive customization options, allowing users to select from over 60 language models supported by LangChain, configure prompts with LangSmith, and choose from more than 100 tools or create their own. It also supports various vector databases and retrieval algorithms, giving users full control over the cognitive architecture of their applications. OpenGPTs currently implements three cognitive architectures: Assistant, RAG (Retrieval-Augmented Generation), and Chatbot, all of which can be modified or extended by users due to the open-source nature of the project. The project supports both Docker-based and traditional Python environment setups, with detailed instructions for installation, configuration, and running the application. It uses Postgres as the default database for storing agent configurations and chat history, with support for vector extensions and migrations managed by golang-migrate. Users can also switch to other vector databases supported by LangChain. The backend is managed with Poetry for dependency management, and the frontend is accessible via a web interface. OpenGPTs aims to provide feature parity with OpenAI's offerings while giving developers more control and flexibility. It includes a sandbox environment for importing, testing, and modifying chatbots, and supports various language models including OpenAI, Azure OpenAI, Anthropic, and Amazon Bedrock. The project also integrates monitoring and debugging tools through LangSmith. Overall, OpenGPTs is a powerful, flexible, and extensible platform for building AI assistants and chatbots with customizable cognitive architectures and extensive tooling support.
https://github.com/langchain-ai/opengpts
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.
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.
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.