fredericlepied/ai-assist

AI assistant with MCP integration, agent skills, knowledge graph, and task scheduling

What's novel

AI assistant with MCP integration, agent skills, knowledge graph, and task scheduling

Code Analysis

8 files read · 2 rounds

A Claude-powered AI assistant framework with MCP integration, scheduled monitoring, a custom workflow language (AWL), knowledge graph, and agent skills for knowledge workers

Strengths

Genuinely novel AWL workflow language with real parser, AST, static analysis, and runtime execution; sophisticated action scheduler with debouncing, resume handling, and event sources; comprehensive security model with command allowlists and path restrictions

Weaknesses

The agent.py file at 168KB is a god object that violates single responsibility; some error handling patterns are inconsistent (e.g., bare Exception catches in action_engine); the codebase is large enough that navigation becomes difficult without strong documentation

Score Breakdown

Innovation

6 (25%)

Craft

82 (35%)

Traction

12 (15%)

Scope

84 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+1

Concept Novelty+2

Craft

Ci+5

Tests+8

Polish+4

Releases+0

Has License+5

Code Quality+24

Readme Quality+15

Recent Activity+7

Structure Quality+5

Commit Consistency+4

Has Dependency Mgmt+5

Traction

Forks+6

Stars+6

Hn Points+0

Watchers+0

Early Traction+0

Devto Reactions+0

Community Contribs+0

Scope

Commits+8

Languages+8

Subsystems+10

Bloat Penalty+0

Completeness+7

Contributors+5

Authored Files+15

Readme Code Match+3

Architecture Depth+5

Implementation Depth+8

Evidence

Commits

145

Contributors

Files

160

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

Apache-2.0