Trending repositories: memory

16 of 16 repositories

• thedotmack/claude-mem

  Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

  AI summary: A persistent memory compression system that captures and injects project context into Claude AI sessions.

  96,035ai-mlTypeScriptApache-2.0aiai-agentsai-memoryanthropic

• Egonex-AI/Understand-Anything

  Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

  AI summary: A highly comprehensive Claude Code plugin designed to instantly accelerate developer onboarding in large codebases.

  85,262developer-toolsTypeScriptMITantigravity-skillsbusiness-knowledgeclaude-codeclaude-skills

• MemPalace/mempalace

  The best-benchmarked open-source AI memory system. And it's free.

  AI summary: A local-first AI memory system providing verbatim storage and semantic retrieval without relying on external API calls.

  59,402ai-mlPythonMITaichromadbllmmcp

• vectorize-io/hindsight

  Hindsight: Agent Memory That Learns

  AI summary: An agent memory system designed to give autonomous AI agents long-term recall and contextual awareness.

  45,429ai-mlPythonMITagentic-aiagentsai-memorymemory

• supermemoryai/supermemory

  Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

  AI summary: A scalable, local-first memory and context engine designed to serve as a personal or company brain for AI applications.

  31,067dataTypeScriptMITagent-memoryai-memorycloudflare-kvcloudflare-pages

• rohitg00/agentmemory

  #1 Persistent memory for AI coding agents based on real-world benchmarks

  AI summary: A persistent memory server for AI coding agents utilizing knowledge graphs and hybrid search.

  29,103developer-toolsTypeScriptApache-2.0agentmemoryagentsaiclaude

• TencentCloud/TencentDB-Agent-Memory

  TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.

  AI summary: A team-level memory hub governing chat, skills, wikis, and code graphs for AI agents.

  27,682dataTypeScriptOtheragentai-agentembeddingllm

• humanlayer/12-factor-agents

  What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

  AI summary: Principles for building production-ready, reliable LLM-powered software and AI agents.

  26,530architectureTypeScriptOther12-factor12-factor-agentsagentsai

• NevaMind-AI/memU

  Personal memory across agents

  AI summary: An agent-driven memory system that curates a shared LLM wiki across different sessions, coding agents, and devices.

  14,492developer-toolsPythonOtheragent-memoryclaude-skillsharnessloop-engineering

• EverMind-AI/EverOS

  One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

  AI summary: A local-first, Markdown-native memory runtime that provides persistent context for AI agents across different applications.

  13,335ai-mlPythonApache-2.0agent-memoryagentic-aiaichats

• holaboss-ai/holaOS

  Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.

  AI summary: A unified, local-first operating system workspace for managing, orchestrating, and interacting with multiple AI agents.

  11,453developer-toolsTypeScriptOtheragentagent-harnessagent-osagentic

• StarTrail-org/PixelRAG

  https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

  AI summary: A scalable visual retrieval-augmented generation framework using web screenshots instead of parsed text.

  10,145ai-mlPythonApache-2.0agentaimemorymultimodal

• unicity-aos/capsule-memory

  Cross-session memory. Reads local memory state and injects it into the system prompt through hooks. Part of Unicity AOS.

  AI summary: A cross-session persistent memory capsule for Astrid OS agents to maintain contextual awareness.

  8,442ai-mlRustApache-2.0ai-agentsmemoryastrid-oscontext-management

• HarnessMD/munder-difflin

  an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions

  AI summary: Multi-agent harness that runs an office of AI coding clones coordinated locally on your machine.

  8,390developer-toolsTypeScriptMITagent-harnessagent-orchestrationagentsai-agents

• memovai/mimiclaw

  MimiClaw: Personal Agent on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS. Hardware agents OS.

  AI summary: A pocket-sized AI assistant that runs entirely on a $5 ESP32-S3 chip utilizing pure C.

  5,777systemsCMITaiassistantclawdbotedge-ai-agents

• deepseek-ai/Engram

  Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

  AI summary: A conditional memory module providing scalable N-gram lookup to enhance LLM context capabilities.

  4,714ai-mlPythonApache-2.0memoryllm-contextdeepseekmodel-architecture