OpenClaw-RL: Train any agent simply by talking

Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design. Awesome-AI-Memory 是一个 集中式、持续更新的 AI 记忆知识库，系统性整理了与 大模型记忆（LLM Memory）与智能体记忆（Agent Memory） 相关的前沿研究、工程框架、系统设计、评测基准与真实应用实践。

LangGraph Mastery Playbook: guided, code-first lessons for building memory-aware LLM agents and workflows with LangGraph, TrustCall, and LangChain.

A collection of pre-build wrappers over common RAG systems like ChromaDB, Weaviate, Pinecone, and othersz!

Local-first memory governance for OpenClaw: Store / Pack / Observe cited, inspectable, rollbackable agent context.

🧠 AI Second Brain — 100% Local Knowledge Management Private, self-hosted second brain. Store, search, and synthesize documents, images, and ideas with local LLMs (LLaVA, CLIP) and PostgreSQL + pgvector. Features multimodal search, knowledge graphs, gDrive streaming, and real-time analysis — all offline, no API keys, no cloud, no limits.

Experimental hierarchical external memory for AI assistants, designed to reduce context contamination and localize memory updates.

Bio-inspired cognitive architecture for LLM agents providing embodied sensation, homeostatic drives, and brain-modeled persistent memory enable cross-session learning without fine-tuning. Works with robots like the Reachy Mini or headless.

Contextual Memory Intelligence for AI Systems - Persistent memory, cognitive tools, and adaptive reasoning capabilities for LLMs (evolved from Clay-CXD)

🧠 Synapse - Supercharge your AI coding assistants with memory, context, MCP tools, and intelligent routing. Works with Cline, Roo, Cursor, and any OpenAI-compatible tool. Just change the API endpoint and get superpowers! ✨

Structured memory for agents: weighted retrieval and replayable evidence paths

Ignis is a locally-ran AI assistant that combines advanced cognitive memory systems with dynamic personality evolution - all while maintaining complete privacy on your hardware.

Memory pipeline using mem0, Qdrant, and Neo4j — ingests GitHub activity, builds an entity knowledge graph, and uses Claude to generate developer insights

A lightweight, pluggable memory backend for agent-based simulations. Supports temporal data, experience replay, and persistent state logging

Local AI assistant architecture with vector memory, identity graph and event-based memory.

MIRA — A memory-integrated multi-agent retrieval system combining vector search, intelligent query planning, reranking, and LLM-powered reasoning for scalable document intelligence.

Per-speaker memory isolation with neural reranking for multi-party LLM agents. 56.3% on LoCoMo (+39.3 pp on temporal over RAG) at 1.9 LLM calls per query.

Research harness for evaluating query-time bounded elimination of reconstructable KV-cache witnesses in long-context transformer inference workloads. Related provisional filing: IN 202641062451.

MnemeBrain Benchmark Suite (BMB): 48 tasks evaluating belief dynamics in AI memory systems — contradiction detection, revision, provenance, and temporal reasoning.

Benchmark for evaluating AI agent memory systems on belief management, cascade propagation, noise resistance, temporal reasoning, token efficiency, and uncertainty abstention — 500 scenarios across 6 dimensions