GitHub repo leaderboard by stars, growth rate and activity.
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
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
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.
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend.
Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.
User Profile-Based Long-Term Memory for AI Chatbot Applications.
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | 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 | JavaScript | 93,582 | last pushed Yesterday | |
| 2 | The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production. | Python | 65,014 | last pushed Yesterday | |
| 3 | 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. | TypeScript | 26,258 | last pushed Yesterday | |
| 4 | One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows. | Python | 12,837 | last pushed 2 days ago | |
| 5 | Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support. | TypeScript | 11,253 | last pushed 2 days ago | |
| 6 | A bio-inspired cognitive memory engine — a new paradigm for Graph RAG. | Python | 4,495 | last pushed 1 week ago | |
| 7 | Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. | TypeScript | 4,487 | last pushed 1 week ago | |
| 8 | OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend. | JavaScript | 3,391 | last pushed 1 year ago | |
| 9 | Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops. | JavaScript | 3,271 | last pushed Yesterday | |
| 10 | User Profile-Based Long-Term Memory for AI Chatbot Applications. | Python | 2,890 | last pushed 8 months ago |
All · 11,474