No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by vshulcz · MCP Server · ★ 925
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is deja-vu safe to install? View the security audit →
Your agents already solved this. deja finds it. vshulcz.github.io/deja-vu Claude Code, Codex, opencode, aider, Gemini CLI, Cursor, Antigravity and Grok Build write every conversation to local files — gigabytes of debugged problems and design decisions you can't search. deja is a zero-dependency binary that turns those histories into a memory layer: — 7–9 ms over gigabytes, retroactive: months of logs from
| Stars | 925 |
| Forks | 89 |
| Language | Go |
| Category | MCP Server |
| License | MIT |
| Quality Score | 67.0422434630531/100 |
| Open Issues | 17 |
| Last Updated | 2026-09-22 |
| Created | 2026-07-14 |
| Platforms | claude-code, cli, codex, gemini, go, mcp |
| Est. Tokens | ~18k |
Looking for a deja-vu alternative? If you're comparing deja-vu with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Bui
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code ·
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown a
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agent
Open-source, Git-native memory for AI coding agents — deterministic local recall for Claude Code, Codex, Curso
Explore other popular mcp server tools:
deja-vu is One memory shared by Claude Code, Codex, Cursor, Copilot CLI, OpenClaw and 29 more coding agents, built from the session history already on disk. A fix found in one agent comes back in any of them, in. It is categorized as a MCP Server with 925 GitHub stars.
deja-vu is primarily written in Go. It covers topics such as agent-memory, ai-memory, claude-code.
You can find installation instructions and usage details in the deja-vu GitHub repository at github.com/vshulcz/deja-vu. The project has 925 stars and 89 forks, indicating an active community.
deja-vu is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to deja-vu on Agent Skills Hub include memorix, swarmvault, memtrace-public. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: