Gridlace
Enables deterministic dependency reasoning over declared graphs, allowing users and AI agents to validate acyclicity, resolve targets, identify runnable parallel layers, assess impact, and explain blockers.
README
Gridlace
A Deterministic Dependency Engine for humans and AI agents.
The name evokes points laced into a changing pattern: move one declared relation and the consequences across the structure change. It is an image, not a claim that the engine uses a regular grid or provides a graph editor.

It answers five questions over relations you declare:
- Is this dependency graph valid and acyclic?
- What remains before these targets can be completed?
- What can run now and in which parallel layers?
- What will these changes affect?
- Why is this target blocked or affected?
The engine proves derivations over declared relations. It does not prove that the declared business relations are true.
This repository is deliberately limited to dependency reasoning. It is not a general orchestration standard, provider-selection framework, task runner, graph discovery system, graph database, or visual graph editor.
Graph contract
{
"schema": "agent-deps/v1",
"nodes": [
{ "id": "schema" },
{ "id": "backend" },
{ "id": "release" }
],
"requires": [
{ "dependent": "backend", "prerequisite": "schema" },
{ "dependent": "release", "prerequisite": "backend" }
]
}
Public edges never use ambiguous from / to keys.
Develop
Use Node.js 22 or newer.
This repository is the public source distribution. It is not currently published to the npm registry.
npm ci
npm run check
npm run start:ui
After npm run check, CLI requests can be run from a clone as operation-specific
JSON read from standard input or an explicit --input file:
node dist/adapters/cli.js resolve --input request.json --pretty
If you install a locally packed copy, the same entry point is available as
dependency-engine.
The MCP server exposes graph_validate, dependency_resolve,
dependency_impact, dependency_slice, and dependency_explain. The local
HTTP adapter exposes matching POST /v1/* routes and GET /health. When the
npm package is installed from a local pack rather than cloned, run the MCP entry point as
node node_modules/@openadam/dependency-engine/dist/adapters/mcp.js.
Start the built local HTTP adapter with:
node dist/adapters/http-server.js --host 127.0.0.1 --port 8787
The HTTP adapter defaults to 127.0.0.1 and is intended for trusted local use.
It does not provide authentication, authorization, or TLS. Do not expose it
directly to an untrusted network; see the security policy.
License
Copyright 2026 openAdam. Licensed under the Apache License 2.0. Bundled browser dependencies are documented in the third-party notices. The license does not grant rights to the Gridlace or openAdam names; see the brand policy.
See the product identity, product model, and review contract for exact boundaries.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.