A Clojure toolkit for building LLM applications, covering prompt templating, prompt chaining, agents and tools, and LLM memory.
ProfSynapse/Professor-Synapse
A prompt and skill package that turns an AI assistant into a guide that gathers your goals, then summons specialized expert agents to help with them.
- Stars
- 3,475
- Forks
- 459
- Open issues
- 13
- Last commit
- 2 months ago
What is it?
Professor Synapse is a set of prompts and skill files for general-purpose AI assistants. It asks targeted questions about your goal, then creates or loads a specialist agent defined by a structured template and hands the conversation to that agent. When a domain is unfamiliar, a Domain Researcher agent browses the web before a new expert is written.
It ships in three forms: a universal prompt you paste into any chat interface, a Claude Desktop skill packaged as a zip, and a portable skill folder that can be placed in a skills directory such as .claude/skills/ or .codex/skills/. The Claude and portable versions share the same core features, including a self-building agent library, persistent memory, and a self-update mechanism that merges new releases while keeping user data.
For complex decisions, a Convener mode brings several agents into a structured debate and then summarizes the trade-offs. Memory is stored in a shared store with per-agent tags, using a working-memory JSON file and a SQLite long-term database with full-text search.
Key features
- 01Gathers context about your goal through targeted questions before choosing an expert.
- 02Creates new specialist agents from a structured template and saves them for reuse.
- 03Convener mode runs multi-agent debates on complex decisions and summarizes trade-offs.
- 04Persistent memory tagged by agent, with SQLite FTS5 search and a Python CLI.
- 05Self-update from GitHub releases that preserves custom agents and memory.
Use cases
- Getting structured guidance on a project or goal in an unfamiliar domain.
- Building a reusable library of specialist agents inside Claude Desktop or another skills-aware assistant.
- Working through a major decision by having several perspectives debate the options.
Quick start
- 1
Open Prompt.md and copy its contents
- 2
Paste the prompt into your AI's system prompt or custom instructions
- 3
Start chatting and tell the assistant what you want to accomplish
Things to know
- No license is listed in the project metadata, so reuse terms are unclear.
- The Claude Skill version requires Claude Desktop with skills support.
In collections
Topics
FAQ
- What is Professor-Synapse?
- A prompt and skill package that turns an AI assistant into a guide that gathers your goals, then summons specialized expert agents to help with them. Professor Synapse is a set of prompts and skill files for general-purpose AI assistants. It asks targeted questions about your goal, then creates or loads a specialist agent defined by a structured template and hands the conversation to that agent. When a domain is unfamiliar, a Domain Researcher agent browses the web before a new expert is written.
- Is Professor-Synapse free to use? What license does it have?
- Professor-Synapse has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
- Is Professor-Synapse still maintained?
- Updated within 6 months. The last commit to Professor-Synapse was on Aug 25, 2026.
- What can I use Professor-Synapse for?
- Getting structured guidance on a project or goal in an unfamiliar domain. Building a reusable library of specialist agents inside Claude Desktop or another skills-aware assistant. Working through a major decision by having several perspectives debate the options.
- How do I install Professor-Synapse?
- Open Prompt.md and copy its contents Paste the prompt into your AI's system prompt or custom instructions Start chatting and tell the assistant what you want to accomplish
- Where can I get Professor-Synapse?
- The source code and installation instructions are on GitHub: https://github.com/ProfSynapse/Professor-Synapse
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A cross-tool skill that makes AI coding agents write less code and less prose, cutting output tokens and LLM API costs.
Lightweight Python framework for building OpenAI-compatible agents with tools, memory, guardrails, tracing, hooks, multi-agent routing and workflows.
A self-hosted personal AI agent platform where a crew of isolated agents shares long-term memory and reaches you through terminal, WhatsApp, Telegram, Slack and more.
A TypeScript framework for building stateful, long-running LLM agents as graphs, with persistence, memory and human-in-the-loop.
A Python plugin for the llm CLI that runs several language models in parallel, iteratively refines their answers, and reaches a consensus via an arbiter model.