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
framerslab/agentos
AgentOS is a TypeScript framework for building agents that retain state across long sessions rather than starting from an empty context each turn. Its central feature is a persistent cognitive memory subsystem modelled on eight mechanisms drawn from memory research, including Ebbinghaus forgetting curves, retrieval-induced forgetting, reconsolidation and source-confidence decay, with episodic, semantic and working memory types selectable per agent. The maintainers publish reproducible benchmark results on LongMemEval, reporting 85.6 percent on the short variant and 70.2 percent on the medium variant, with a separate public benchmark repository and leaderboard. A second distinguishing feature is runtime tool forging: when an agent hits a gap its static toolkit cannot cover, it writes a TypeScript function with a Zod schema, an LLM judge reviews the specification, and the approved function executes inside a hardened node virtual machine sandbox before joining the tool catalogue for the rest of the session. Beyond memory and tools the framework provides six orchestration strategies for multi-agent collaboration, a guardrails architecture, a voice pipeline, optional HEXACO personality vectors that shape how an agent behaves, and a single dispatch interface over eleven model providers with automatic provider detection from environment variables. More than a hundred extensions and eighty-eight skills load automatically at startup. Sessions keep a lossless transcript of assistant tool calls, tool results and thinking blocks independently of the memory subsystem, bounded by whole-block eviction past roughly 120 thousand tokens, with a reseed call for atomic history replacement in long tool-driving loops. The package installs from npm as @framers/agentos and is documented with a quickstart, an examples cookbook and an API reference. It targets TypeScript developers building assistants, tutors or agent teams that must stay coherent over many turns.
https://github.com/framerslab/agentos
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.