#1313th of 15 in Memory

tencentdb-agent-memory

Shared memory server for coding agents: chat memory, skills, wiki, code graph

Stars: 27.8k
License: custom license
Last commit: Sep 2026
Last release: Aug 2026
Language: TypeScript

Missed the latest GitHub check; these facts may be older.

Overview

Memory service behind a proxy: point an agent's base URL at it and it extracts layered chat memory (L0 to L3), reusable Skills, a document Wiki and a CodeGraph of repositories. Memory Hub is a web panel for teams, ownership, private/team/ACL visibility and binding assets to specific agents. Listed clients include Claude Code, Codex, CodeBuddy, Hermes and OpenClaw.

Who it is for: Teams running coding agents who want shared, persistent memory across sessions

Strengths

Proxy integration needs no plugin, hook or MCP server in the agent
Layered L0-L3 memory with BM25, vector and RRF retrieval, capped by budget
Per-asset ownership, versions and private/team/restricted ACL visibility
Cold-start import of codebases, documents and past conversation sessions

Weaknesses

Setup runs three services and needs two sets of LLM parameters in .env
CodeGraph mainly supports public HTTPS repositories; private repos still being refined
Agent binding is manual; automated memory routing is still under iteration
License detected as NOASSERTION while the README badge says MIT

What it needs

Needs Node.js >=22.16, LLM API (memory and proxy parameter sets), MongoDB (experimental, optional)
Models: Configurable LLM via .env (providers unknown)
port 8125

Also in Memory

See all 15

Also in Memory
Rank	Project	Score
1	gbrainLong-term memory store for coding agents, with sources and corrections30.9k starsMIT	83 out of 100
2	hindsightAgent memory server with retain, recall and reflect operations49.7k starsMIT	79 out of 100
3	MemPalaceLocal long-term memory store for agents with verbatim storage and semantic search59.6k starsMIT	77 out of 100
#4	CogneeMemory engine that turns documents and code into a knowledge graph32.3k starsApache-2.0	77 out of 100
#5	OpenVikingFilesystem-style context database for agent memory, resources and skills Live demo ↗ (opens in a new tab)39.9k starsAGPL-3.0	74 out of 100

How to choose

Check what gets stored (raw messages, extracted facts, graphs) and how it is retrieved.
Multi-tenant isolation matters if several users or agents share one store.
Look at the backing store (Postgres, a vector DB, a graph DB) and whether you already run it.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

custom license Custom terms

Use it at work: Check
Change it and rebrand it: Check
Sell it or host it for others: Check

Your part: GitHub could not match these terms to a standard license. Read the license before you use it at work, rebrand it or host it for others.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#13 of 15 in Memory on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/tencentcloud/tencentdb-agent-memory.svg)](https://archestack.com/best-of-ai/projects/tencentdb-agent-memory/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-ai/tencentdb-agent-memory/" title="tencentdb-agent-memory on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with tencentdb-agent-memory filled in.