Registry › Compare › AI Town vs TencentDB Agent Memory

AI Town vs TencentDB Agent Memory

TencentDB Agent Memory leads on trust: 60.5/100 (Grade C) against 50.6/100 (Grade C), a 9.9-point gap. TencentDB Agent Memory leads on supply-chain integrity and maintenance.

C AI Town 50.6

A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.

a16z-infra/ai-town · #995 overall · #8 Needs review · coverage C (2/5)

AI Town doesn't lead on any scored dimension in this pair.

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.

TencentCloud/TencentDB-Agent-Memory · #692 overall · #5 Needs review · coverage C (2/5)

Choose TencentDB Agent Memory if supply-chain integrity and maintenance matter most.

  • +3.1Safety / Integrity: 78% of recent commits signed, against 26%
  • +2.5Maintenance
  • +1.1Adoption: 31.1k GitHub stars against 10.8k

Where they differ

6.4
Safety / IntegrityTencentDB Agent Memory +3.1
9.5
12.0
TransparencyTencentDB Agent Memory +0.3
12.3
13.7
MaintenanceTencentDB Agent Memory +2.5
16.2
9.7
AdoptionTencentDB Agent Memory +1.1
10.8
-2.0
Runtime calibrationTencentDB Agent Memory +2.9
+0.9

1 dimension identical: Identity 10.8 · Full evidence table

An independent, evidence-based trust comparison of AI Town and TencentDB Agent Memory, two Needs review projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal AI Towna16z-infra/ai-town TencentDB Agent MemoryTencentCloud/TencentDB-Agent-Memory
HVTrust score 50.6 60.5
Evidence grade C C
Coverage grade C C
Overall rank #995 #692
Rank in Needs review #8 #5
GitHub stars 10.8k 31.1k
Last updated 2d ago 3d ago
Build provenance No No
OSSF Scorecard 4.1 / 10 4.5 / 10
License MIT NOASSERTION
Downloads — —
Trust dimensions (points earned)
Safety / integrity / 25 6.4 9.5
Identity & provenance / 18 10.8 10.8
Transparency / 17 12.0 12.3
Maintenance / 20 13.7 16.2
Adoption / 20 9.7 10.8
Runtime capability surface (full matrix)
MCP server — Implemented
External providers 3 — OpenAI, Replicate, Together AI 2 — Anthropic, OpenAI
Requires API keys Yes No
Plugin surface — plugins
Provenance drift — —
Open in the live compare tool → AI Town profile TencentDB Agent Memory profile More Needs review →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →