memory

Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane: Centralised tools, MCPs, models, data, and policies with consistent observability and governance.

On-device memory layer for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.

🧠 Production-grade memory sidecar for AI agents — gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-tested. | 生产级外挂记忆系统，兼容Hermes/Claude/Cursor等任意AI智能体

Personal OS agent that learns who you are, detects life patterns, and grows smarter about you every day. Memory + Cron + Atropos RL

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Apache-2.0, ships as library / MCP server / HTTP cluster.

A list of AI memory projects（ AI长期记忆的开源和商业项目列表）

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

ChatIndex: Tree indexing and retrieval for long conversational memory

Shared Memory Storage for Multi-Agent Systems

A general AI agent framework that can be adapted to various tasks and environments.

Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG. Finds what RAG misses. Zero cloud, zero cost.

Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.

A companion guide for the blog post series, LangChain Decoded.

Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.

SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A3B FP8 ~240 tok/s, 27B-int4 hybrid GDN+Mamba, Gemma4 26B/31B AWQ, 256K ctx. 321 patches: TurboQuant k8v4 KV, MTP/DFlash spec-decode, FULL cudagraph, hybrid GDN. vLLM pin dev424 + Control Center GUI.

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.

Implementation of Memformer, a Memory-augmented Transformer, in Pytorch

A context harness for AI agents: all your scattered context — code, memory, docs, databases, SaaS — in one searchable, browsable, file-like interface.

A general-purpose Python framework for building LLM agents and multi-agent systems. "Four lines of code, an agent with memory."