Skip to main content
aitoolsatlas.ai
BlogAbout

Explore

  • All Tools
  • Comparisons
  • Best For Guides
  • Blog

Company

  • About
  • Contact
  • Editorial Policy

Legal

  • Privacy Policy
  • Terms of Service
  • Affiliate Disclosure
Privacy PolicyTerms of ServiceAffiliate DisclosureEditorial PolicyContact

© 2026 aitoolsatlas.ai. All rights reserved.

Find the right AI tool in 2 minutes. Independent reviews and honest comparisons of 890+ AI tools.

  1. Home
  2. Tools
  3. Decision Node
OverviewPricingReviewWorth It?Free vs PaidDiscountAlternativesComparePros & ConsIntegrationsTutorialChangelogSecurityAPI
Developer Tools🔴Developer
D

Decision Node

MCP server that records development decisions as structured JSON, embeds them as vectors, and enables semantic search over past decisions.

Starting at$0/month
Visit Decision Node →
💡

In Plain English

MCP server that records development decisions as structured JSON, embeds them as vectors, and enables semantic search over past decisions.

OverviewFeaturesPricingUse CasesLimitationsFAQAlternatives

Overview

Decision Node is a Developer Tools MCP server that records development decisions as structured JSON, embeds them as vectors, and lets AI coding tools semantically search prior decisions, with the DecisionNode software offered free while Gemini API usage may incur separate usage-based costs. It is built for developers and teams using Claude Code, Cursor, Windsurf, Antigravity, or any MCP client who want persistent project memory without relying on chat history.

DecisionNode focuses on a narrow but important workflow: preserving architecture, product, UI, and implementation decisions so future AI coding sessions can retrieve them before generating code. The website describes a decision flow where a choice such as “use our custom dropdown, not the native one” is stored as a typed JSON object with fields like id, scope, decision, rationale, and constraints. That record is then embedded with Gemini’s gemini-embedding-001 model and stored locally in vectors.json. When a later AI session needs context, it can call the search_decisions MCP tool, embed the new query, compare it with stored vectors using cosine similarity, and return the closest matches with similarity scores. The example on the site shows a 94% match for a prior UI decision.

The tool is not just a simple note-taking layer. It includes a CLI, an MCP server, local storage, global decisions that apply across projects, history tracking, conflict detection, and a local web UI launched with decide ui. The UI includes three specific views: a force-directed graph of similar decisions, a 2D vector space using UMAP projection of 3072-dimensional embeddings, and a searchable list. The website also states that matched nodes pulse live in the color of the MCP client that searched, which makes retrieval activity visible while Claude Code, Cursor, Windsurf, Antigravity, or another MCP client is working.

Compared to the 870+ AI tools in our directory, DecisionNode is unusually specific: it is not a broad AI coding assistant, documentation platform, or generic vector database. It is best understood as a shared structured memory layer for AI-assisted development. Teams should consider it when repeated decisions are being lost between AI sessions, when ADR-style notes are too disconnected from the coding workflow, or when multiple AI coding clients need to search the same local memory. It is less suitable for teams that need hosted collaboration, provider choice for embeddings, or deep integrations with existing documentation tools such as ADR repositories, Notion, or internal knowledge bases, because the website emphasizes local vectors.json storage, Gemini embeddings, and MCP-based retrieval rather than cloud synchronization.

🎨

Vibe Coding Friendly?

▼
Difficulty:intermediate

Suitability for vibe coding depends on your experience level and the specific use case.

Learn about Vibe Coding →

Was this helpful?

Key Features

Structured Decision Capture+

DecisionNode stores decisions as typed JSON objects rather than unstructured notes. The website example includes id, scope, decision, rationale, and constraints, which gives future AI sessions enough context to understand both the choice and why it was made.

Semantic Search via MCP+

AI coding tools can call the search_decisions MCP tool to retrieve relevant prior decisions. Search is based on vector similarity, so a future query about a settings dropdown can surface an earlier decision about using a custom selector even if the wording differs.

Gemini Vector Embeddings+

DecisionNode uses Gemini’s gemini-embedding-001 model to convert decision text into vectors. The website states that these embeddings are 3072-dimensional and stored locally in vectors.json.

Local Web UI+

Running decide ui launches a local interface with three views: a force-directed graph, a 2D vector space using UMAP projection, and a searchable list. The site also says matched nodes pulse live in the searching client’s color, making AI retrieval activity visible.

Governance Controls+

DecisionNode includes configurable similarity thresholds, global decisions, history tracking, conflict detection, and deprecate/reactivate workflows. Conflict detection checks existing decisions at 75% similarity before adding a new one, which helps catch duplicates and contradictions.

Pricing Plans

Free

$0/month

  • ✓MIT-licensed software
  • ✓MCP server for AI coding tools
  • ✓CLI install via npm i -g decisionnode
  • ✓Structured JSON decision storage
  • ✓Semantic search with Gemini gemini-embedding-001 embeddings
  • ✓Local web UI with graph, vector space, and list views
  • ✓No hosted Decision Node subscription tier identified
  • ✓Requires a user-managed Gemini API key for embeddings; Google lists gemini-embedding-001 at free of charge on the Gemini API free tier, $0.15 per 1M input tokens on paid Standard, and $0.075 per 1M input tokens on paid Batch
See Full Pricing →Free vs Paid →Is it worth it? →

Ready to get started with Decision Node?

View Pricing Options →

Best Use Cases

🎯

Recording UI implementation choices, such as requiring a custom ScopeSelector instead of a native datalist, so future AI sessions follow the same browser and theme constraints.

⚡

Maintaining architecture decisions across Claude Code, Cursor, Windsurf, Antigravity, and other MCP clients when developers switch tools during the same project.

🔧

Creating global project rules such as “never commit .env files” so the same decision appears in every project search instead of being rediscovered per repository.

🚀

Auditing how decisions changed over time using the history log, including which client made the change rather than seeing only a generic MCP source.

💡

Exploring relationships between decisions in the local web UI using the force-directed graph, 2D UMAP vector projection, and searchable list views.

🔄

Reducing repeated AI mistakes in long-running codebases where chat history is not enough to preserve rationale, constraints, and prior implementation choices.

Limitations & What It Can't Do

We believe in transparent reviews. Here's what Decision Node doesn't handle well:

  • ⚠Decision retrieval is explicit, so the AI must call the MCP search_decisions tool; decisions are not automatically injected into every prompt.
  • ⚠Embeddings use Gemini’s gemini-embedding-001 model, so teams that require OpenAI, local, or self-hosted embeddings do not appear to have a provider choice based on the website content.
  • ⚠Decision vectors are stored locally in vectors.json, which supports on-premises use but does not provide built-in cloud sync or team collaboration.
  • ⚠The tool depends on consistent decision capture; if developers or AI clients do not record decisions, there will be little useful memory to retrieve.
  • ⚠The website does not describe direct integrations with ADR tools, Notion, Confluence, GitHub Issues, or other existing documentation systems.

Pros & Cons

✓ Pros

  • ✓Semantic search finds relevant decisions even with different terminology
  • ✓Works across all major AI coding tools via MCP
  • ✓Local storage keeps sensitive decisions on-premises
  • ✓Visual UI helps teams explore decision relationships
  • ✓Structured format prevents decisions from becoming unstructured brain dumps

✗ Cons

  • ✗Requires a Gemini API key for vector embeddings (adds dependency and cost)
  • ✗Only useful if the team consistently records decisions — needs adoption discipline
  • ✗Local-only storage means no built-in team sync or cloud collaboration
  • ✗Vector embeddings are Gemini-specific — no choice of embedding provider
  • ✗No integration with existing decision documentation tools (ADR tools, Notion, etc.)

Frequently Asked Questions

What does DecisionNode actually store?+

DecisionNode stores development decisions as structured JSON rather than as loose markdown notes. The website example includes fields such as id, scope, decision, rationale, and constraints, which makes each record easier for AI tools to interpret later. It then embeds the decision text as a vector and stores it locally in vectors.json. This makes the decision searchable by meaning, not just by exact keywords.

Which AI coding tools does DecisionNode work with?+

The website explicitly lists compatibility with Claude Code, Cursor, Windsurf, Antigravity, and any MCP client. Because it exposes an MCP server, the retrieval workflow depends on the AI coding client calling the search_decisions tool. The site also notes that retrieval is explicit: decisions are not automatically injected into the system prompt. This is useful for developers who want searchable memory without permanently bloating every prompt.

Is DecisionNode free?+

Yes. The website schema lists DecisionNode as accessible for free, with an offer price of 0 USD, and identifies the license as MIT. The install URL points to the npm package decisionnode, and the homepage shows installation via npm i -g decisionnode. Users should still account for the Gemini embedding dependency: Google lists gemini-embedding-001 as free of charge on the Gemini API free tier, $0.15 per 1M input tokens on paid Standard, and $0.075 per 1M input tokens on paid Batch.

How does DecisionNode find related decisions?+

DecisionNode converts decision text into embeddings using Gemini’s gemini-embedding-001 model, then compares future queries against stored vectors using cosine similarity. The website states that embeddings are 3072-dimensional and that the web UI can project them into a 2D vector space using UMAP. It also supports a configurable minimum similarity threshold to filter out irrelevant results. The example workflow on the site shows a prior UI decision returned with a 94% similarity score.

Can DecisionNode prevent duplicate or conflicting decisions?+

DecisionNode includes conflict detection before adding a new decision. According to the website, existing decisions are checked at 75% similarity so near-duplicates and contradictions can be caught. This does not replace human review, because the team still needs to decide whether two records truly conflict. It does, however, create a useful guardrail when many decisions accumulate across multiple AI coding sessions.
🦞

New to AI tools?

Read practical guides for choosing and using AI tools

Read Guides →

Get updates on Decision Node and 370+ other AI tools

Weekly insights on the latest AI tools, features, and trends delivered to your inbox.

No spam. Unsubscribe anytime.

Alternatives to Decision Node

Notion

No-Code & Automation

All-in-one workspace that combines notes, databases, wikis, project management, and AI-powered writing into a flexible block-based platform for individuals and teams

Confluence

Knowledge & Documents

AI workspace for knowledge management and team collaboration from Atlassian.

Mem0

AI agent memory

Memory infrastructure for AI agents and applications, available as an open-source framework and managed platform.

View All Alternatives & Detailed Comparison →

User Reviews

No reviews yet. Be the first to share your experience!

Quick Info

Category

Developer Tools

Website

decisionnode.dev
🔄Compare with alternatives →

Try Decision Node Today

Get started with Decision Node and see if it's the right fit for your needs.

Get Started →

Need help choosing the right AI stack?

Take our 60-second quiz to get personalized tool recommendations

Find Your Perfect AI Stack →

Want a faster launch?

Explore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.

Browse Agent Templates →

More about Decision Node

PricingReviewAlternativesFree vs PaidPros & ConsWorth It?Tutorial

📚 Related Articles

Best AI Developer Tools in 2026: 15 Tools Tested and Ranked

I ran a six-week evaluation of 15 AI developer tools across four workloads: a Flask-to-FastAPI refactor, a Next.js dashboard built from scratch, 23 bug-fix issues sampled from SWE-bench Verified, and a Rust-to-Go port of a 600-line CLI. **Rankings reflect what shipped working cod

2026-05-19T02:06:15Z15 min read

5 Undiscovered AI Tools Atlas Worth Trying in March 2026

Hidden gems in the AI agent tooling space — from browser infrastructure to memory platforms to observability tools. These production-ready tools solve real problems that most developers haven't discovered yet.

2026-03-105 min read