HN Showcase
Back to browse
GitHub Repository

Philosopher-based prompt system for multi-editor AI agent routing

1 starsJavaScript

Agent Historic Philosophical Persona Routing and Prompts

by sosuke·May 5, 2026·5 points·2 comments
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainNiche Gem

Philosopher personas for AI routing when CrewAI and AutoGen already do agent orchestration.

Strengths
  • •Judge-mediated deliberation council for ambiguous tasks adds genuine decision-making depth.
  • •Adversarial verification pipeline for high-stakes implementations shows serious engineering.
  • •DOI-backed whitepaper indicates rigor beyond typical prompt libraries.
Weaknesses
  • •Prompt routing is solved territory — LangChain, AutoGen, CrewAI all do persona-based agent orchestration.
  • •Core value is prompt content, not novel technology or architecture.
Category
AI/ML
Target Audience

Developers using AI coding assistants

Similar To

CrewAI · AutoGen · LangChain

Post Description

I've been building this for a while. The core of it is I've assigned different tasks in a software engineering job to different philosophers. The prompts are written toward their thinking by "them" but the keywords are generic. I absolutely love using this prompt system. I share it every chance I get. I wrote a whitepaper about it. Maybe ya'll would be interested in it. I find my experience is better with my prompts than without.

The only thing you might not like is my heavy handed treatment of logging output. I was seriously fed up with LLMs trying to run huge tests or scripts and then looking at just the last 20 characters. Everything is logged out to files and then the files are queried for the answers it wants.

Similar Projects

Developer Tools●●Solid

NadirClaw, LLM router that cuts costs by routing prompts right

If you're burning through Claude/OpenAI credits, this is a low-friction stopgap: it classifies prompts in ~10ms and routes trivial tasks to cheaper/local models while reserving premium APIs for complex work. The agentic-task detection, reasoning-aware routing, session pinning and context-window fallback are practical touches that avoid mid-thread model bouncing and 429 failures. It isn't reinventing the space (OpenRouter and others exist), but it's focused on real-world cost tradeoffs and drop-in compatibility.

Solve My ProblemNiche Gem
amirdor
113mo ago
Developer Tools●●Solid

Kbot – AI agent that forges its own tools at runtime (MIT, $0)

Terminal agent that writes persistent CLI tools when it hits capability gaps.

WizardryBold Bet
isaacsight
202mo ago