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
DataBassGit/AgentForge
AgentForge is a versatile low-code framework designed to facilitate the rapid development, testing, and iteration of AI-powered autonomous agents and cognitive architectures. It supports a wide range of large language models (LLMs), including popular APIs from OpenAI, Google's Gemini, Anthropic's Claude, as well as local models through Ollama and LMStudio, allowing users to run different models for different agents based on their specific needs. This flexibility makes AgentForge suitable for both beginners seeking an accessible entry point into AI agent development and experienced developers aiming to build complex, model-agnostic, and database-flexible autonomous agents. The framework offers extensive customization options, enabling users to tailor agents to specific use cases with ease. It supports the creation of custom tools and actions, dynamic prompt templates that adapt to various contexts, and on-the-fly prompt editing without requiring system restarts. AgentForge's architecture is designed to be LLM agnostic, providing seamless integration with multiple LLM APIs and open-source local models. AgentForge also incorporates ChromaDB as its vector store implementation, adding memory capabilities to agents for enhanced performance. The comprehensive documentation covers installation, usage, core concepts such as agents, API integration, personas, settings, storage, tools and actions, and utilities, making it easier for users to get started and explore advanced features. The project encourages community contributions and is actively seeking collaborators, particularly for UI/UX development to create a front-end interface. Licensed under the GNU General Public License v3.0, AgentForge is an open-source initiative aimed at advancing the development of intelligent autonomous agents with a flexible, extensible, and user-friendly framework.
https://github.com/DataBassGit/AgentForge
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.