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
seanpixel/Teenage-AGI
Teenage-AGI is a Python-based project inspired by Auto-GPT-related projects, especially BabyAGI, and the research paper "Generative Agents: Interactive Simulacra of Human Behavior." The project aims to create an AI agent that possesses memory and the ability to "think" before taking actions, such as generating text outputs. It leverages OpenAI's language models and Pinecone's vector database to store and retrieve memories persistently, allowing the AI to retain knowledge even after being shut down. The AI processes user queries by vectorizing them and storing them in Pinecone, then searches its memory for relevant past queries and memories. It "thinks" about the appropriate action, stores this thought, and generates a response based on both the thought and relevant memories. This response, along with the query, is then saved back into the memory database. The project includes commands like "read" and "think" to feed information or insert memories into the agent, enhancing its interactive capabilities. Users can run the AI locally by cloning the repository, installing dependencies, setting up API keys for OpenAI and Pinecone, and running the main script. Additionally, the project supports running in a Docker container for isolated environments. The developer has experimented with GPT-4, noting that the AI can remember its identity and maintain coherent conversations without a context window. The project is a personal initiative by a college student and startup founder, motivated by the idea that much of human language generation happens internally, and thus AGI should similarly have an internal thought process. The project credits the inspiration from the Generative Agents paper and acknowledges contributions from the community.
https://github.com/seanpixel/Teenage-AGI
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.