TencentCloud releases TencentDB Agent Memory: local long-term memory for AI agents
TencentCloud has open-sourced TencentDB Agent Memory, a TypeScript library providing fully local long-term memory for AI agents via a 4-tier progressive pipeline with no external API dependencies. The project has accumulated 5,785 GitHub stars with 172 added on the day of observation. It targets the growing need for persistent, private memory in agent systems without reliance on third-party services.
Related guides (2)
Related events (8)
agentmemory: Persistent Memory for AI Coding Agents
agentmemory is an open-source TypeScript library providing persistent memory for AI coding agents, designed based on real-world benchmarks. The repository has accumulated 13,772 total stars with a notable single-day gain of 1,626 stars, indicating strong community traction. It targets the agent tool ecosystem by addressing memory continuity across coding agent sessions.
claude-mem: Persistent Cross-Session Memory Layer for AI Coding Agents
claude-mem is an open-source TypeScript library that provides persistent context across sessions for AI coding agents. It captures agent activity during sessions, compresses it using AI, and injects relevant context into future sessions. The tool claims compatibility with Claude Code, OpenAI Codex, Gemini, GitHub Copilot, and other coding agents. The repository has accumulated 78,579 stars with 319 added today, indicating strong community traction.
supermemoryai/supermemory: Fast Scalable Memory Engine and API for AI Applications
supermemory is an open-source TypeScript project providing a memory engine and API designed for AI-era applications, emphasizing speed and scalability. It has accumulated 23,282 GitHub stars with 236 added today, indicating active community interest. The project targets the growing need for persistent, retrievable memory layers in AI agents and applications.
MemOS: Self-Evolving Memory OS for LLM Agents with Hybrid Retrieval and Token Savings
MemOS is an open-source TypeScript project providing a memory operating system layer for LLM and AI agents, featuring ultra-persistent memory, hybrid retrieval, and cross-task skill reuse. The project claims 35.24% token savings through its memory management approach. It has accumulated 9,329 GitHub stars with moderate daily momentum (+67). The system targets agent memory persistence and efficiency as a foundational infrastructure component.
MemPalace: open-source AI memory system trending on GitHub
MemPalace is an open-source Python library positioning itself as a highly-benchmarked AI memory system, currently trending on GitHub with over 53,000 stars. The project claims benchmark leadership among open-source memory systems for AI agents. High star count suggests significant community adoption or interest in persistent memory tooling for AI applications.
ByteDance UI-TARS-desktop: open-source multimodal AI agent stack gains traction on GitHub
ByteDance's UI-TARS-desktop is an open-source TypeScript project described as a multimodal AI agent stack connecting AI models and agent infrastructure. The repository has accumulated 36,677 GitHub stars with 148 new stars on the day of observation. It represents ByteDance's public contribution to the agentic tooling ecosystem.
Honcho: Memory Library for Stateful AI Agents Gains Traction on GitHub
Honcho is an open-source Python library by Plastic Labs designed to provide memory infrastructure for building stateful AI agents. The repository has accumulated 4,004 total stars with a notable single-day gain of 140 stars, indicating growing community interest. It addresses the persistent state and memory management problem in agent architectures.
basic-memory: persistent memory layer for AI conversations via MCP
basic-memory is an open-source Python project providing persistent memory for AI conversations, allowing users to avoid re-explaining context across sessions. The project has accumulated 3,212 GitHub stars with modest daily growth. It appears to implement a local knowledge-graph or note-based memory store exposed via MCP or similar tooling.