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
langchain-ai/langchainjs
LangChain.js is a comprehensive framework designed for building applications powered by large language models (LLMs) with a focus on composability and context-aware reasoning. It enables developers to create sophisticated applications that can understand and utilize context from various sources such as prompt instructions, few-shot examples, and external content to ground their responses. The framework supports reasoning capabilities, allowing language models to decide how to answer questions or what actions to take based on the provided context. The project is implemented in TypeScript and is compatible with multiple environments including Node.js, Cloudflare Workers, Vercel/Next.js, Supabase Edge Functions, browsers, and Deno. LangChain.js is part of a larger ecosystem that includes open-source libraries, production tools, and deployment platforms. It offers modular components and integrations that can be used independently or as part of the full LangChain framework. Key components include core abstractions, third-party integrations, chains, agents, and retrieval strategies that form the cognitive architecture of applications. LangGraph.js, a related project, enables the creation of stateful agents with streaming and human-in-the-loop support, facilitating the development of robust multi-actor applications. LangChain.js supports various use cases such as question answering over documents, chatbots, and data-augmented generation. It provides off-the-shelf chains for common tasks and modular components for customization and building new chains. The framework emphasizes ease of use, extensibility, and production readiness, with tools like LangSmith for monitoring and optimizing applications and LangGraph Cloud for deploying production-ready APIs and assistants. The project is open-source under the MIT license and encourages community contributions. It is designed to integrate seamlessly with the Python version of LangChain, allowing serialization and sharing of objects across languages. Extensive documentation, tutorials, and examples are available to help developers get started and build advanced LLM-powered applications.
https://github.com/langchain-ai/langchainjs
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.
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.