ImFeH2/autopoe

A structured multi-agent framework for coordinated AI collaboration

What's novel

A structured multi-agent framework for coordinated AI collaboration

Code Analysis

15 files read · 4 rounds

A desktop application (Tauri + React + Python) that orchestrates multiple LLM-powered agents collaborating with a human through threaded discussions, with sandboxed command execution, persistent memory, and per-agent task management.

Strengths

Genuinely well-architected hexagonal design with platform-specific OS-level sandboxing (bubblewrap/seatbelt/restricted tokens), thoughtful LLM prompt engineering that prevents agent loops, and a complete end-to-end system from JSONL protocol to SQLite persistence to desktop UI.

Weaknesses

The tools module is a 22KB monolith that could be split, the README is a single sentence that barely describes the system's capabilities, and some production-safety concerns exist (assert statements in the store, no visible rate limiting on LLM calls).

Score Breakdown

Innovation

5 (25%)

Craft

50 (35%)

Traction

4 (15%)

Scope

54 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+1

Concept Novelty+1

Craft

Ci+5

Tests+8

Polish+1

Releases+4

Has License+5

Code Quality+25

Readme Quality+8

Recent Activity+7

Structure Quality+5

Commit Consistency+2

Has Dependency Mgmt+5

Traction

Forks+0

Stars+6

Hn Points+0

Watchers+0

Early Traction+0

Devto Reactions+0

Community Contribs+0

Scope

Commits+8

Languages+8

Subsystems+13

Bloat Penalty+0

Completeness+7

Contributors+5

Authored Files+15

Readme Code Match+3

Architecture Depth+7

Implementation Depth+8

Evidence

Commits

205

Contributors

Files

193

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

Apache-2.0