Ross ROSS = Recommend OSS · open-source software intelligence for agents

thedotmack/claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More observed · 2026-10-18

github.com/thedotmack/claude-mem · homepage · TypeScript · Apache-2.0 (permissive) observed · 2026-10-18

Health v2 · maintenance only

82/100

  • Activity 100
  • Release rhythm 88
  • Longevity 29
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.

  • gap_med: 0
  • age_days: 415
  • days_rel: 3
  • days_push: 3
  • n_releases_24m: 368

Full methodology

Adoption not part of the score

101435 stars · 8893 forks observed · 2026-10-18

What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-21, confidence 0.97

Claude-Mem (Grok Mem) is an open‑source memory engine that captures, compresses, and stores observations from AI agents across sessions. It provides a local SQLite store with optional cloud sync via a private MCP link.

Use cases

  • keep AI agents aware of previous actions without re‑prompting
  • store and retrieve session history for Claude, Gemini, or other LLM agents
  • synchronize agent memory across multiple devices and IDEs
  • enable searchable, vector‑based recall of past observations
  • automate context injection for continuous AI workflows

When to choose

  • you need persistent, searchable memory for LLM agents
  • you prefer a local‑first solution with optional secure cloud sync
  • your workflow spans multiple tools (IDE, CLI, mobile) that support MCP
  • you want to reduce token usage by reusing past context

When to avoid

  • you require a fully managed, enterprise‑grade memory service out of the box
  • your project is not based on JavaScript/Node.js ecosystems
  • you need real‑time high‑throughput vector search beyond SQLite capabilities

Facets

library · maturity active

vector-database search-engine api-framework cli artificial-intelligence browser cli persistent-context agent-memory local-first mcp rad grok-mem claude-mem memory ai-agents retrieval-augmented-generation nodejs docker

7 sources

Member repositories

RepositoryRoleHealth v2
thedotmack/claude-memmain82

For agents

markdown · JSON · MCP: product_card(name="thedotmack/claude-mem")

Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem