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
ray-r-ren/agent-apprenticeship
Agent Apprenticeship is an open ecosystem and command-line tool built around the idea of turning real agent work into reusable learning signals. Apprentice agents complete real-world tasks through iterative workflow loops, are evaluated by mentor agents, users, or human experts, and each finished workflow generates structured experience that can improve future runs. The project frames this as a compounding exchange: economically valuable task execution produces training signals, those signals improve later work, and that work creates new reusable experience for the shared ecosystem. Users install it via npx or globally as the apprentice command, then configure an apprentice agent, a mentor model provider, and an apprenticeship mode (Autonomous, Expert-Led, or Organization Custom). It auto-detects installed local agent CLIs including Codex, Cursor, Claude Code, OpenClaw, OpenCode, and Hermes Agent, and also supports a custom command template; mentor model provider keys for OpenAI, Anthropic, Gemini, or OpenRouter are stored in a local env file. A typical flow runs a task, watches progress, then inspects and exports the generated Experience Compilation, and installs runtime training from prior experience for reuse in later runs. Contribution can be set to a public ecosystem or private internal-only mode, with commands to search, inspect, and pull shared experience. A seed dataset published on Hugging Face includes hundreds of curated tasks and full experience compilations plus thousands of execution traces and work episodes. It targets practitioners who want their local agents to learn from accumulated task execution across domains.
https://github.com/ray-r-ren/agent-apprenticeship
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.