thedotmack/claude-mem
Claude-Mem is a plugin for Claude Code that captures, compresses, and preserves coding session context to enable persistent memory and continuity across sessions.
Awesome AI Agents › Continual Learning Agents
USC-GVL/Agent-Driver
Agent-Driver is an innovative autonomous driving system that leverages Large Language Models (LLMs) to bring human-like intelligence and reasoning capabilities to the task of driving. Unlike traditional autonomous driving frameworks that rely on perception-prediction-planning pipelines, Agent-Driver introduces a paradigm shift by using LLMs as cognitive agents. This approach integrates a versatile tool library accessible through function calls, a cognitive memory that stores common sense and experiential knowledge, and a reasoning engine capable of chain-of-thought reasoning, task planning, motion planning, and self-reflection. The system is designed to mimic human-level driving by incorporating intuitive common sense and robust reasoning, enabling more nuanced and interpretable decision-making. The project is evaluated on the large-scale nuScenes benchmark, where it significantly outperforms state-of-the-art driving methods. It also demonstrates superior interpretability and few-shot learning abilities compared to existing approaches. The repository provides detailed instructions for installation, data preparation using pre-cached nuScenes data, and training, which involves fine-tuning a GPT-based motion planner using OpenAI's API. Users need to register for an OpenAI API account and configure their API keys to run the system. The fine-tuning process is designed to be cost-effective, with options to use a subset of the training data. Inference and evaluation scripts are included to facilitate testing and performance assessment on the nuScenes validation set. The project emphasizes transparency and reproducibility, providing notebooks and scripts for running the entire pipeline or individual components. Overall, Agent-Driver represents a significant advancement in autonomous driving by embedding human-like cognitive functions into the driving process, making it a promising direction for future research and development in the field.
https://github.com/USC-GVL/Agent-Driver
Also in Continual Learning Agents
vectorize-io/hindsight
Hindsight is an agent memory system designed to create smarter, learning AI agents, addressing limitations of traditional memory techniques like RAG and knowledge graphs.
langchain-ai/langchainjs
LangChain.js is a TypeScript framework for building context-aware, reasoning applications powered by large language models, offering modular components, chains, agents, and tools for production and deployment.
aden-hive/hive
Hive is an outcome-driven agent development framework designed for evolving agents with AI evaluation, human-in-the-loop, and self-improvement capabilities.
aiming-lab/MetaClaw
Proxy-based layer that turns everyday conversations with a personal agent into learning signals, injecting skills per turn and running scheduled reinforcement learning updates without a local GPU.
kayba-ai/agentic-context-engine
Agentic Context Engine (ACE) is a framework that enables AI agents to autonomously learn from their successes and failures, continuously improving their performance across various tasks without additional training data or fine-tuning.
AgentDock/AgentDock
AgentDock is an open-source framework for building sophisticated AI agents with configurable determinism, enabling reliable and creative AI applications through a node-based architecture and multi-stage workflows.
modelscope/AgentEvolver
Self-evolving agent training framework from ModelScope that combines automatic task generation, experience-guided exploration and attribution-based credit assignment into one reinforcement learning stack.