#memory Repositories
193 repositories total
Deepseek Harness, an OpenClaw knowledge graph memory plugin. Invited to present at a Tsinghua University symposium in April 2026. Knowledge Graph + Memory; Knowledge Graph Context Engine for OpenClaw โ extracts structured triples from conversations, compresses context by 75%, and enables the reuse of experience across sessions.
Read and write process memory in Node.js (Windows API functions exposed via Node bindings)
OpenMemory Chrome Extension: Long-term memory for ChatGPT, Claude, Perplexity, Grok etc
Your repo remembers: local-first AI memory and context control plane for developers and coding agents.
The open source agentic content system to make your contents alive. Self-hosted on any platform. โ
Turn stateless LLMs into a stateful, compounding AI agent. Local-first persistent memory, quantitative decision screens, and governance harness across Claude Code, Antigravity, Cursor, and VS Code. Own the state. Rent the intelligence.
A bitmap memory usage monitor for Android. An Android image memory analysis tool that can help discover whether an application's image usage is reasonable.
Multi-scenario AI Workbench: six-layer overview + topology connection diagram + public workbench template (ready to run in four scenarios; copy the source code as-is and use it) + memory mechanism. Companion marketplace: https://www.mydsh.xyz . Author: https://linyujia.me . Note: It doesnโt work right out of the box; you need to configure and test the scenarios with your own content.
Self-maintaining, Obsidian-compatible knowledge base for pi โ turn raw sources into an interlinked wiki that compounds. Native Open Knowledge Format (OKF) v0.2.
Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.
Secure memory management for AI Agents โข Ensures data integrity โข Reduces hallucinations โข Maintains consistent long-term context
๐ฅ๐ฅ๐ฅ Turn AI-written code into real apps. Nubase is an open-source, AI-native backend platform for AI Coding, agentic applications, and modern product teams: Memory, Database, Storage, and Auth in one self-hostable service.
Give your AI agent a brain that remembers. Local memory system for Claude Code โ 100% private, GPU-accelerated, zero cloud dependency.
Type-safe tools, on-device inference, multi-agent workflows, memory, and guardrails, in one Swift-native runtime
A curated solutions to building a self-evolving second brain that helps AI agents understand your personal and team context.
Use your NVIDIA GPU's VRAM as swap space on Linux. Built for laptops with soldered memory and no upgrade path. If you have an RTX card sitting there with 8GB of VRAM and you're getting swapped to SSD, this puts that VRAM to work
Give your AI a body and a touch of humanity โ a QQ companion that remembers and reads the room, plus an MCP that can control Android phones
One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.
Free Grok Bot alternative that runs on your own models. Use the ChatGPT, Claude, or Grok subscription you already pay for, and get a team of bots each with its own memory and computer.
[ICLR 2026] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
Plugin-first long-term memory for agent platforms โ reference implementation of AMP (Agent Memory Protocol).
RadeonTuner is an easy-to-use alternative to AMD Adrenalin Software for users who just want the basics and use the driver-only software installation option.
Memory Bridge MemoryBridge โ A cross-device, cross-platform shared memory layer for AI | Cross-device and cross-platform shared memory for AI (CDSMP implementation)
๐ DSH Fish Memory: Give conversations a long-term memory that gradually fades, with a timestamp on every entry. The โfishโ in the name comes from DeepSeekโs whale.
Local long-term memory for Hermes, Codex, Claude Code, WorkBuddy, and dsh agents: one SQLite store, source-backed recall, and tools to inspect, correct, or delete what is remembered.
This is a high performance list view for React Native with support for complex layouts using a similar FlatList usage to make easy the replacement. This list implementation for big list rendering on React Native works with a recycler focused on performance and memory usage and so it permits processing thousands items on the list.
Self-hosted Enterprise and Personal AI + agent runtime in .NET (NativeAOT-friendly)
Hermes-style persistent memory and learning loop for Pi coding agent
Open source AI company OS. 38 roles, 6 templates, 4-layer memory. Your AI company remembers everything โ locally. npx clawcompany
Memory Palace for AI โ persistent memory, identity, and multi-project orchestration for Claude Code
Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice โ runnable as a library, a daemon, or a real-time pipeline.