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.
- stars
- 26,887
- 30-day movement
- +366122/day
- Related entries
- 60
- Connections
- 1
TencentDB Agent Memory is a team-level memory hub for AI Agents that converts conversations, docs, and code into four reusable memory assets: Chat Memory, Skill, LLM-Wiki, and Code-Graph. It is a TypeScript repository from TencentCloud, tagged with embedding, vector-search, and local-first long-term memory, and includes an OpenClaw plugin.
Reach for it when multiple agents or frameworks need governed, shared long-term memory rather than isolated per-agent context.
Use it to
- Store agent conversations as reusable Chat Memory
- Turn documentation into a shared LLM-Wiki
- Build a Code-Graph from codebases for agent retrieval
- Share and govern memory assets across a team's agents
- Equip agents with skills via the OpenClaw plugin
For Teams building multi-agent systems needing shared memory
- Role
- agent-app
- Language
- TypeScript
- Licence
- custom (licence file present)
- Forks
- 2,536
- Open issues
- 232
- Last push
- 2026-09-15
- Latest release
- v0.1.4 · 2026-04-23