# TencentCloud/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.

Repository: https://github.com/TencentCloud/TencentDB-Agent-Memory
Canonical: https://ross.abutalabs.com/products/tencentdb-agent-memory
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: agent, llm, memory, openclaw-plugin, ai-agent, embedding, local-first, long-term-memory, vector-search
Last push: 2026-08-26T09:20:15+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 10
- inputs: {"age_days": 148, "days_push": 7, "days_rel": 8, "gap_med": 14, "n_releases_24m": 10}
- flags: young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 24677, forks 2269 (observed 2026-08-28T04:11:37.557682+00:00)

## What it is
TencentDB Agent Memory is a self-hosted team-level memory hub for AI agents that converts conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph). It runs as a memory server with a proxy so multiple agents and frameworks share one governed, searchable memory store.

## Use cases
- give my ai agents long-term memory across sessions
- share memory between multiple ai agents on a team
- store agent conversations and docs as searchable memory
- build a code graph memory for coding agents
- self-host a memory server for claude code
- turn chat history into reusable agent skills
- add vector search memory to my llm agent

## When to choose
- you run multiple agents or frameworks and want one shared memory server
- you want team-level, governed memory assets like skills and wikis
- you prefer self-hosting with local-first vector search

## When to avoid
- you need a fully managed cloud memory service with zero ops
- you only need simple per-session context windows without persistence
- you cannot run Docker or Node.js services

## Facets
- artifact type: service
- maturity: active
- function: vector-database, rag, agent-framework, llm-inference, search-engine, plugin-system, self-hosted
- domain: artificial-intelligence, large-language-models, databases, developer-tools, self-hosted
- platform: self-hosted, cross-platform
- tags: agent-memory, long-term-memory, memory-hub, team-memory, code-graph, llm-wiki, openclaw-plugin, claude-code, local-first, embeddings, ai-agents, retrieval-augmented-generation, docker, nodejs, web-server

## Member repositories
- TencentCloud/TencentDB-Agent-Memory (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:37.557682+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:56:10.327053+00:00, confidence not recorded.
  - readme: https://github.com/TencentCloud/TencentDB-Agent-Memory (fetched 2026-08-28T04:11:37.557682+00:00, sha 435008ee62c1)
- Data as of 2026-08-30T08:39:29.467469+00:00.