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
vectorize-io/hindsight
Hindsight is an advanced agent memory system focusing on enabling AI agents to learn and evolve over time, rather than merely recalling conversation history. It aims to overcome the shortcomings of conventional memory solutions such as Retrieval-Augmented Generation (RAG) and knowledge graphs. The system has reportedly achieved state-of-the-art performance on the LongMemEval benchmark, demonstrating high accuracy in long-term memory tasks for conversational AI. Hindsight is currently utilized in production environments by Fortune 500 companies and numerous AI startups. The platform offers flexible integration options, including an LLM Wrapper for quick adoption with just two lines of code, and a more granular API for greater control over memory storage and recall. It supports various LLM providers such as OpenAI, Anthropic, Gemini, Groq, Ollama, LM Studio, and Minimax, and can be deployed via Docker or as an embedded Python solution. Hindsight is particularly well-suited for conversational AI agents and autonomous task-performing agents, especially those requiring complex learning capabilities akin to humans, such as AI employees. It supports use cases like personalized per-user memories and chat history, allowing for enhanced personalization and data isolation through custom metadata. The system's architecture emphasizes creating a robust and scalable memory foundation for sophisticated AI applications.
https://github.com/vectorize-io/hindsight
Also in Continual Learning Agents
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.
ghostwright/phantom
Self-hosted persistent AI co-worker built on the Claude Agent SDK that runs on its own machine with long-term memory, self-evolution, an MCP server and Slack, Telegram, email and web channels.