agent-memory vs TencentDB-Agent-Memory
Persistent memory for AI coding agents compared
agent-memory organizes coding-session notes into tiered knowledge and generates AGENTS.md context for new threads. TencentDB-Agent-Memory is a self-hostable team hub that turns conversations, documents, and code into assets agents can share. The main difference is a file-based, focused memory workflow versus a broader hub with asset management and access controls.
agent-memory: Give Coding Agents Persistent, Tiered Memory
agent-memory turns coding-session notes into organized, tiered knowledge and generates an AGENTS.md section with relevant context for new threads. It is a TypeScript tool for teams and developers who want agents to reuse knowledge without relying on manual searches.
TencentDB-Agent-Memory: Share Reusable Memory Across AI Agents
TencentDB Agent Memory is a team memory hub that turns conversations, documents, and code into reusable assets for AI agents. It suits teams that want agents to share curated context and skills across sessions and frameworks.
| agent-memory | TencentDB-Agent-Memory | |
|---|---|---|
| Language | TypeScript | TypeScript |
| License | — | NOASSERTION |
| Stars | 7 | 27.7k |
| Forks | 0 | 2.7k |
| Last analyzed | Oct 4, 2026 | Oct 3, 2026 |
Key differences
- agent-memory focuses on session notes, LLM consolidation, and tiered AGENTS.md output; TencentDB-Agent-Memory also handles conversations, documents, code, Skills, Wiki, and CodeGraph.
- agent-memory stores memory as files and offers a CLI with adapter-based integration; TencentDB-Agent-Memory provides a self-hostable hub and proxy for supported agent clients.
- agent-memory uses hot, warm, and cold tiers, with hot memory inlined and warm memory listed; TencentDB-Agent-Memory manages assets with owners, visibility controls, and agent bindings.
- agent-memory documents Bun-based standalone use, while TencentDB-Agent-Memory documents Node.js 22.16 or newer and a Docker deployment path.
- Both are TypeScript projects. The supplied facts list 7 stars and 0 forks for agent-memory, and 27.7k stars and 2.7k forks for TencentDB-Agent-Memory.
- TencentDB-Agent-Memory has a GitHub license status of NOASSERTION despite an MIT badge in its README; agent-memory's supplied facts do not specify a license.
Choose agent-memory if you…
- want a focused workflow for carrying coding-session knowledge into new threads through generated AGENTS.md content.
- prefer file-based memory and a CLI with adapter-based integration.
- need to capture, consolidate, and reorganize project notes into hot, warm, and cold tiers.
Choose TencentDB-Agent-Memory if you…
- need a shared memory hub for multiple people or agents, with asset ownership and access controls.
- want to turn conversations, documents, and code into reusable Skills, Wiki content, or CodeGraph indexes.
- plan to self-host a hub and proxy, and can configure its LLM parameters and deployment requirements.
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.