claude-mem vs TencentDB-Agent-Memory
Cross-harness session memory: hooks capture what the agent does, an LLM compresses it into observations, and the next session gets the relevant ones back via progressive-disclosure MCP tools. — versus — Tencent's team memory hub for agents: an API proxy turns conversations, docs and code into shared chat memory, skills, an LLM wiki and a code graph, reused across agents.
Both capture what agents do and compress it into memory. claude-mem uses hooks for one user; TencentDB uses an API proxy and serves a team.
| claude-mem | TencentDB-Agent-Memory | |
|---|---|---|
| Stars | 113k | 31k |
| Forks | 9.8k | 3.0k |
| Language | JavaScript | TypeScript |
| License | Apache-2.0 | NOASSERTION |
| Last activity | yesterday | 2 days ago |
| Topics | memory, coding | memory, gateway |
| Curated connections | 12 | 4 |
claude-mem — the curator's take
The most widely installed of the capture-and-reinject memory plugins, and the one with the most product around it: 5 lifecycle hooks, a Bun worker with an HTTP API and live web viewer, SQLite plus FTS5 plus Chroma for hybrid search, and a 3-layer MCP search pattern (index → timeline → full detail) that keeps recall at ~50-100 tokens per hit until you actually want the body. Installs into Claude Code, OpenCode, Antigravity, OpenClaw and more, with `<private>` tags to keep things out of the store and optional cloud sync. The tradeoffs: it spends model tokens summarizing every session, it drags in Bun and uv, and what you get back is a generated observation rather than the raw transcript — if you want auditable, greppable memory you can edit by hand, look at the Markdown-first options instead.
TencentDB-Agent-Memory — the curator's take
Use it when a team wants every agent (Claude Code, CodeBuddy, others) to share governed memory with zero integration: point the base URL at its proxy and memory is captured. Skip it if routing all LLM traffic through a proxy is unacceptable, or for a single developer: it runs three services and needs two LLM configs. Team Memory is in beta and the MongoDB backend is experimental; the license is custom.