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
ysymyth/awesome-language-agents
The project "ysymyth/awesome-language-agents" is a curated list and comprehensive compilation of language agents based on the framework called Cognitive Architectures for Language Agents (CoALA). This framework is detailed in a research paper that outlines a structured approach to designing language agents with distinct action spaces and decision-making cycles. The CoALA framework divides the action space of language agents into two main parts: external actions that allow interaction with external environments (grounding), and internal actions that manage internal memories such as reasoning, retrieval, and learning. The internal memory system includes short-term working memory and optional long-term memories like episodic, semantic, and procedural memories. The decision-making process in CoALA involves planning and execution stages, where the agent iteratively proposes, evaluates, and selects actions to affect either its internal memory or the external world. The repository provides links to the CoALA paper, a tweet thread summarizing the framework, and a BibTex file containing over 300 related citations. It also includes a selection of relevant academic papers that have contributed to the development and understanding of language agents, categorized by their focus on reasoning, grounding, retrieval, or learning. These papers cover a wide range of topics such as human-AI interaction, robotic affordances, multimodal reasoning, embodied agents, and self-refinement techniques. This project serves as a valuable resource for researchers and developers interested in the design, implementation, and study of language agents. It offers a structured overview of the state-of-the-art in language agent architectures and provides extensive references to foundational and recent works in the field. The repository encourages community contributions through pull requests to expand and refine the list of papers and resources.
https://github.com/ysymyth/awesome-language-agents
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.
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.