Structured, queryable memory for development decisions.
Stores architectural choices as vector embeddings, exposes them to AI agents via MCP.
Your AI keeps forgetting what you agreed on. You say "use Tailwind, no CSS modules" — next session, it writes CSS modules. DecisionNode stores these decisions as vector embeddings so the AI can search them before writing code.
Not a markdown file. A queryable memory layer with semantic search.
npm install -g decisionnode
cd your-project
decide init # creates project store
decide setup # configure Gemini API key (free tier)
# Connect to Claude Code (run once)
claude mcp add decisionnode -s user decide-mcp- A decision is made — via
decide addor the AI callsadd_decisionthrough MCP - Embedded as a vector — using Gemini's
gemini-embedding-001, stored locally invectors.json - AI retrieves it later — calls
search_decisionsvia MCP, gets back relevant decisions ranked by cosine similarity
The retrieval is explicit — the AI calls the MCP tool to search. Decisions are not injected into a system prompt.
CLI (decide) |
MCP Server (decide-mcp) |
|
|---|---|---|
| For | You | Your AI |
| How | Terminal commands | Structured JSON over MCP |
| Does | Setup, add, search, edit, deprecate, export, import, config | Search, add, update, delete, list, history |
Both read and write to the same local store (~/.decisionnode/).
decide add # interactive add
decide add -s UI -d "Use Tailwind" # one-command add
decide add --global # applies to all projects
decide search "error handling" # semantic search
decide list # list all (includes global)
decide deprecate ui-003 # soft-delete (reversible)
decide activate ui-003 # bring it back
decide check # embedding health
decide embed # fix missing embeddings
decide export json > decisions.json # export to fileFull docs at decisionnode.dev/docs
- Quickstart
- CLI Reference — all commands
- MCP Server — 9 tools, setup for Claude/Cursor/Windsurf
- Decision Nodes — structure, fields, lifecycle
- Context Engine — embedding, search, conflict detection
- Configuration — storage, search sensitivity, global decisions
- Workflows — common patterns
For LLM consumption: decisionnode.dev/decisionnode-docs.md
The CLI and MCP server are just the start. There's a VS Code extension, a marketplace for shared decision packs, and cloud sync being worked on — contributions to any of these are welcome.
Whether it's a bug fix, a new feature, improving the docs, or just starring the repo — all help is appreciated. See CONTRIBUTING.md for how to get started.
MIT — see LICENSE.