workflowstacks
mcp-server

deja-vu: Recall Solutions

Find previously solved problems with deja-vu, a tool for startup founders using coding agents. Boost productivity with retroactive search.

From the repo · “Coding agent memory for Claude Code, Codex, Cursor and 39 more, built from the session history already on your disk. Local search, MCP and hooks, no LLM, one Go binary.”

1,277 stars+76★ this week142 forksGoGuide quality 8/10 · reviewed Jul 23Updated 10/22/2026100% free · open source
What it does

Deja-vu helps startup founders find previously solved problems by their coding agents using retroactive search, boosting productivity

When to use it
  • •When you have multiple coding agents working on similar problems and want to avoid duplicated effort
  • •When you need to recall a previously solved problem but can't remember the exact solution
  • •When you want to measure the impact of your coding agents' work and identify areas for improvement
Ready-to-paste prompt
./deja-vu -query 'error handling in Go' -agents myagent1,myagent2
Heads up: Make sure you have the correct runtime version of Go installed, as deja-vu is built with Go and may not be compatible with older versions
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/deja-vu && curl -fsSL https://workflowstacks.com/api/skills/deja-vu/claude-skill -o ~/.claude/skills/deja-vu/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How deja-vu: Recall Solutions works
Codeflow
Free to inspect

Deja-vu: Recall Solutions is a very large Go project (~491k lines across 3479 code files, plus 23 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~491k lines · 3479 code files · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 7 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Go · Docker
Go 98%JavaScript 2%Python 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    cmd/deja/main.go
    Where the program starts running
  3. 3
    internal/index/index.go
    Inside internal/ — the main logic begins here
What's in each folder
internal/Core code — the actual logic1496 files
skills/Prompts, skills & agent definitions1 files
cmd/Command-line entry points1868 files
extensions/Sub-packages / plugins79 files
docs/Documentation242 files
scripts/Helper scripts93 files
fixtures/Data files88 files
claude-plugin/Folder11 files
READMEHas testsDocumentedCI checksDocker readyMIT licenseUpdated this month
Quick Actions
Details
Creator
vshulcz
Language
Go
Category
mcp-server
Published
7/14/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/deja-vu.svg)](https://workflowstacks.com/skills/deja-vu?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

MCP config

Sequential Thinking MCP config

Give Claude a structured, step-by-step reasoning scratchpad.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 355,695
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,361
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 131,266
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 544
MisakaNet: Share AI Debugging Insights
Founders get a micro-lesson library for AI agents to share and search debugging experience. For founders using Python and AI agents.
mcp-server★ 1,470
agents – Build No‑Code AI Assistants with 2‑Way Sync
Launch AI assistants or multi‑agent workflows fast using a visual builder or TypeScript SDK. Perfect for founders who need scalable, self‑hosted AI agents. 1.5k+ GitHub stars.
mcp-server★ 313
DashClaw: Enforce AI Agent Policies and Get Auditable Decisions
DashClaw lets founders control AI agents with guard policies, approval workflows, and built‑in audit trails—perfect for regulated AI ops.