AgentIndex icon
AgentIndex
selvedge logo
selvedge
★ 25
vs
world-model-mcp logo
world-model-mcp
★ 24

selvedge vs world-model-mcp

selvedge: Selvedge provides long-term memory for AI-coded codebases, capturing the 'why' behind agent-made changes directly from the agent's context. It acts as a local MCP server, logging structured events to a SQLite database, allowing developers to query the reasoning for code modifications years later.; world-model-mcp: World Model MCP is a temporal knowledge graph designed to provide long-term memory and context for AI coding agents. It prevents hallucinations, stops repeated mistakes, and reduces regressions by validating code changes against learned constraints and re-injecting relevant context.

01

TL;DR

selvedge logo
selvedgeDev Tooling · ★ 25

Understanding the historical 'why' behind schema decisions and migrations in long-term AI-coded projects.

Read selvedge full review →
world-model-mcp logo
world-model-mcpCode Assistant · ★ 24

Enhance AI coding agents (like Claude Code, Cursor, Continue) with a persistent, harness-neutral memory layer to improve code quality.

Read world-model-mcp full review →
02

Side-by-Side Comparison

Field
selvedge logoselvedge
world-model-mcp logoworld-model-mcp
Category
Dev Tooling
Code Assistant
Stars
★ 25
★ 24
License
MIT
MIT
Install Command
pip install selvedge && cd your-project && selvedge setup
pip install world-model-mcp && cd /path/to/your/project && python -m world_model_server.cli setup
Updated
5d ago
1mo ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Agent Memory, Code Provenance, Git Blame for AI
AI Agent Memory, Temporal Knowledge Graph, Code Validation
03

Features

selvedge logoselvedge
01Live capture of agent reasoning and intent directly from the agent's context.
02Tracks changes at an entity-level (e.g., DB columns, API routes, environment variables) rather than just lines of code.
03Stores all change events and reasoning locally in a durable, queryable SQLite database.
04Provides CLI tools for blaming, diffing, searching, and managing the history of AI-generated code changes.
05Exports and imports change history compatible with the open Agent Trace v0.1.0 standard.
world-model-mcp logoworld-model-mcp
01Prevent Hallucinations: Validates API/function references against known entities before use.
02Stop Repeated Mistakes: Learns constraints from corrections and applies them in future sessions.
03Reduce Regressions: Tracks bug fixes and warns when changes touch critical regions.
04Survive Compaction: Re-injects top constraints and recent facts after the agent's context window resets.
05Resolve Contradictions: Picks a winner between conflicting facts using confidence, recency, or source count.
04

Use Cases

selvedge logoselvedge
↳Understanding the historical 'why' behind schema decisions and migrations in long-term AI-coded projects.
↳Providing an audit trail for AI-generated code changes, essential for compliance (e.g., SOC 2, EU AI Act).
↳Helping solo developers recall the purpose of AI-generated code in their side projects or internal tools.
↳Enforcing checks for prior attempts on entities to prevent agents from re-introducing reverted decisions.
↳Tracking the full scope of a feature or task across multiple entities and commits using changesets.
world-model-mcp logoworld-model-mcp
↳Enhance AI coding agents (like Claude Code, Cursor, Continue) with a persistent, harness-neutral memory layer to improve code quality.
↳Automate code validation and linting based on project-specific rules and learned patterns, reducing developer effort in code review.
↳Prevent the re-introduction of previously fixed bugs and enforce architectural constraints across development sessions.
↳Manage and track factual information about a codebase over time, enabling temporal queries and evidence-based reasoning.
↳Deploy self-hosted memory for agents in cloud environments (e.g., Claude Managed Agents) using HTTP transport.
FAQ

FAQ

What is the difference between selvedge and world-model-mcp?
Both selvedge and world-model-mcp are in the Dev Tooling category. selvedge has 25 stars, while world-model-mcp has 24 stars.
Which is better, selvedge or world-model-mcp?
The best choice depends on your use case. Choose selvedge if Understanding the historical 'why' behind schema decisions and migrations in long-term AI-coded projects., and world-model-mcp if Enhance AI coding agents (like Claude Code, Cursor, Continue) with a persistent, harness-neutral memory layer to improve code quality..
Is selvedge free or open source?
Yes, selvedge is open source on GitHub (MIT).
Is world-model-mcp free or open source?
Yes, world-model-mcp is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to selvedge →Alternatives to world-model-mcp →selvedge details →world-model-mcp details →