whereismyai
TencentDB Agent Memory
TencentDB Agent Memory is a team-level memory hub that turns conversations, documents, and code into reusable memory assets for AI agents.
TencentDB Agent Memory is a team-level memory hub for AI agents that turns conversations, documents, and code into four reusable memory assets: Chat Memory, Skill, LLM-Wiki, and CodeGraph. It allows multiple AI agents and team members to share and maintain accumulated experience, reducing repetitive work across sessions. The system extracts chat memory and skills from conversations, converts documents into a structured wiki, and indexes codebases to show call relationships and impact paths. It supports zero-code integration through a proxy, allowing various agent frameworks to connect without plugins or hooks. It is designed for development teams and individual creators who want their agents to inherit past project context and work continuously.
TencentDB Agent Memory at a glance
Key features
- Automatic asset extraction from conversations and tasks
- Chat memory that retains preferences and facts
- Skill library with versions, trigger boundaries, and validation rules
- LLM-Wiki that turns product docs into structured pages
- CodeGraph that indexes symbols, files, and impact paths
- Human-controlled memory panel for team management and access control
- Cold-start import for existing codebases, documents, and conversation sessions
Use it for
- Importing existing codebases to automatically index call relationships and impact paths
- Distilling successful workflows into reusable skills for the entire team
- Converting product docs and design specs into a structured knowledge map
- Equipping different agents with specific memory assets and permissions
Alternatives to TencentDB Agent Memory
- Tigerless Agent Memory — Maintains agent history in portable, greppable Markdown files without API keys.
- Agentmemoryrepo — Enables agents to navigate memories like a wiki and share knowledge across sessions.
- Memori — Reduces LLM token usage and spend by over 97% with targeted recall.
- Mem0 — It provides drop-in persistent memory for AI agents without changing pipelines.
- AI Memory — Shared memory for coding agents that works across machines and team members.
- ReMe — It enables local-first, file-native long-term memory sharing across multiple AI agents.
- memU — It gives every connected agent a shared and inspectable memory layer.
- MemOS — It delivers ultra-persistent memory, hybrid-retrieval, and token savings.
- Playground — Persists agent memory across sessions and searches by meaning.
- Agent Beacon — Retains coding agent knowledge across tools so errors do not repeat.
- Supermemory — Integrates long-term memory into AI coding agents with a single prompt.
- EverOS — It enables agents to learn from experience and improves over time without manual coding.
All TencentDB Agent Memory alternatives