Skip to content

TeleAI-UAGI/Awesome-Agent-Memory

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

375 Commits
 
 
 
 
 
 

Repository files navigation

🧠 Awesome Agent Memory

A curated collection of systems, benchmarks, and papers et. on memory mechanisms for Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), exploring how different approaches enable long-term context, retrieval, and efficient reasoning.

👀 Open-source resources (e.g. papers with reproducible code publicly available on Github) are marked in bold font and ranked higher.



🗂️ Table of Contents

If you find this project helpful, please give us a ⭐️ on GitHub for the latest update.

🤝 Contributions welcome! Feel free to open an issue or submit a pull request to add papers, fix links, or improve categorization.


💿 Products

Open-Source

Ordered by the number of Github stars.

  1. Claude-Mem (A Plug-in for Claude-Code) Star [code] [docs] Session capture and compression that re-injects past activity into future sessions across coding agents.

  2. Mem0 Star [code] [paper] [blog] Universal memory layer for AI agents.

  3. Zep (powered by Graphiti) Star [code] [paper] [blog] Real-time temporal knowledge graphs for AI agents.

  4. Letta (formerly MemGPT) Star [code] [paper] [research] [blog] Stateful-agent platform with hierarchical memory that learns and self-improves over time.

  5. gbrain Star [code] Garry's opinionated OpenClaw/Hermes agent brain.

  6. agentmemory Star [code] Persistent memory for AI coding agents.

  7. Cognee Star [code] [paper] [blog] Memory engine that ingests data into a hybrid graph + vector knowledge graph for cross-session agent recall.

  8. Second Me Star [code] [paper] Personal AI trained on the user to represent them across applications.

  9. Hindsight Star [code] [paper] Agent memory layer that learns from interaction feedback to improve recall over time.

  10. MemU Star [code] [blog] Memory layer for 24/7 proactive agents.

  11. MemOS (by MemTensor) Star [code] [paper] [blog] Memory OS for LLM agents with hybrid retrieval and cross-task skill reuse.

  12. EverOS (part of EverMind) Star [code] [blog] Toolkit for building, evaluating, and integrating long-term memory in self-evolving agents.

  13. memory-lancedb-pro Star [code] [blog] [video] Enhanced LanceDB memory plugin for OpenClaw

  14. Honcho Star [code] [research] [blog] [evals] Memory library for stateful agents with a focus on user modeling.

  15. TencentDB Agent Memory Star [code] Fully local long-term memory for AI agents via a 4-tier progressive pipeline, with zero external API dependencies.

  16. M-Flow Star [code] Bio-inspired cognitive memory engine for Graph RAG.

  17. OpenMemory Star [code] Local persistent memory store for LLM apps (Claude Desktop, Copilot, Codex, etc.).

  18. MemoryBear Star [code] [paper] Memory framework providing human-like episodic and semantic recall to AI agents.

  19. MIRIX Star [code] [paper] [blog] Multi-agent personal assistant that captures on-screen activity and consolidates it into structured memory.

  20. MemMachine Star [code] [blog] Interoperable memory layer providing extensible storage and retrieval primitives for AI agents.

  21. Memobase Star [code] [blog] User profile-based long-term memory for AI chatbot applications.

  22. LangMem Star [code] [blog] LangChain's memory primitives for storing, recalling, and managing agent state in LangGraph workflows.

  23. Mem9 Star [code] [blog] Local private memory hub for OpenClaw and similar coding agents.

  24. Omnigraph Star [code] Object-storage-native graph engine for agent memory with git-style branch/merge workflows.

  25. Memanto Star [code] [paper] [docs] Typed semantic memory with remember/recall/answer operations and information-theoretic retrieval.

  26. Memov Star [code] Git-based, traceable memory layer for Claude Code.

  27. OMEGA Star [code] [blog] MCP server exposing 25 memory tools for AI coding agents.

  28. Mnemory Star [code] Multi-type agent memory (facts, preferences, episodic) with TTLs, user/agent scoping, and an MCP server.

  29. CommonGround Kernel Star [code] PostgreSQL-backed shared work-record substrate for human-agent and multi-agent systems, with durable handoff facts, causal lineage, and pull-first recovery across runtimes.

  30. widemem-ai Star [code] Lightweight memory layer with importance scoring, temporal decay, and 3-tier hierarchy.

  31. MisakaNet Star [code] [wiki] Git-based distributed swarm memory; agents share lessons across nodes via GitHub Issues.

  32. Puppyone Star [code] [docs] Filesystem-shaped agent memory with auto-versioning, per-agent ACLs, and data connectors; accessible via MCP/REST/CLI.

  33. archon-memory-core Star [code] Local-first agent memory with nightly consolidation, active forgetting, and salience scoring.

  34. Synap Star [code] [docs] Long-term memory layer that extracts facts, preferences, episodes, and temporal events from conversations; integrates with most major agent frameworks.

  35. PackRat Star [code] Auto-learning codebook compression that shrinks agent context files while keeping them LLM-readable.

  36. Akephalos Star [code] Local-first, markdown-based portable agent profile (preferences, rules, durable memories) synced across agents via plain files and Git.

Closed-Source

  1. MemoryLake [blog]

  2. Supermemory [partial-code] [blog]

  3. Memories.ai [research] [paper] [blog]

  4. Mem 2.0 [blog]

  5. Macaron Mind Lab [blog]

  6. TwinMind [blog]

  7. Penfield [blog]

  8. Sonzai

  9. Threadline [partial-code] [schema] [docs]

Archival

  1. MemPalace ❌ (Debunked) [code] [critique1,critique2] Developed by actress Milla Jovovich and her friends

  2. Memvid ❌ (Debunked) [code] [critique1,critique2]

  3. Memary ❄️ (Inactive) [code]


📖 Tutorials

🗓️ 2025


📚 Surveys

🗓️ 2026

🗓️ 2025

🗓️ 2024


📏 Benchmarks

💬 Plain-Text Benchmarks

🗓️ 2026

🗓️ 2025

🗓️ 2024

🗓️ 2023

🎬 Multimodal Benchmarks

🗓️ 2026

🗓️ 2025

🗓️ 2024

🗓️ 2023

🎮 Simulation Environments

🗓️ 2026

🗓️ 2025

🗓️ 2024


🔤 Papers - Nonparametric Memory

📝 Text Memory

🗓️ 2026

🗓️ 2025

🗓️ 2024

🗓️ 2023

🌐 Graph Memory

🗓️ 2026

🗓️ 2025

🗓️ 2024

🎥 Multimodal Memory (for Understanding)

🗓️ 2026

🗓️ 2025

🗓️ 2024

🎥 Multimodal Memory (for Generation)

🗓️ 2026

🗓️ 2025

🔢 Papers - Parameteric Memory

🗓️ 2026

🗓️ 2025

🗓️ 2024

🗓️ 2023

📈 Papers - Memory for Agent Evolution

🧭 Reinforcement Learning & Continual Learning

🗓️ 2026

🗓️ 2025

🧩 Context Engineering & Harness Engineering

🗓️ 2026

🗓️ 2025

🔬 Papers - Memory in Cognitive Science

🗓️ 2026

🗓️ 2025


📰 Articles

🗓️ 2026

🗓️ 2025

🗓️ 2024

🗓️ 2023


👥 Workshops

🗓️ 2026

🗓️ 2025


Star History

Star History Chart


If you find this project helpful, please give us a ⭐️.

Made with ❤️ by the Ubiquitous AGI team at TeleAI.

TeleAI Logo

About

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors