syne

# Syne 🧠

**AI Agent Framework with Unlimited Memory**

*"I remember, therefore I am"*

Named after [Mnemosyne](https://en.wikipedia.org/wiki/Mnemosyne), the Greek goddess of memory and mother of the Muses.

Syne is a standalone, open-source AI agent framework built in Python. It features **PostgreSQL-native memory** with semantic search, an **ability-based architecture** for extensibility, and **self-evolution** capabilities where the agent can create new abilities for itself.

---

## Why Syne?

Most AI assistants forget everything between sessions. They have no persistent memory, no learning, no growth. Syne is different:

- **Unlimited memory** — Semantic search over millions of memories using pgvector + knowledge graph for entity-relation traversal
- **Anti-hallucination** — 3-layer defense ensures only user-confirmed facts are stored
- **Self-evolving** — Syne can create new abilities for itself (with your permission)
- **No runtime config files** — No SOUL.md or CONFIG.yaml. All runtime behavior lives in PostgreSQL, changed through conversation
- **Near-zero cost** — Chat via Google Gemini OAuth (free). Embedding + memory evaluator via Ollama (local, $0). Entire stack can run at $0/month
- **Linux-style permissions** — 3-digit octal permissions (owner/family/public) for every tool and ability
- **Interactive CLI** — Terminal-based chat with persistent memory and tools
- **Remote nodes** — Extend Syne to multiple machines via WebSocket. Each node has its own CLI (`syne cli`), one shared memory for all, controlled from one Telegram bot

---

## Minimum Requirements

| Requirement | Details |
|-------------|---------|
| **CPU** | 1 vCPU minimum (2+ recommended for Ollama embedding + evaluator) |
| **OS** | Linux (Ubuntu 22.04+, Debian 12+) |
| **Python** | 3.11+ |
| **RAM** | 2 GB minimum (Ollama loads one model at a time, ~1.3 GB per model). 4 GB recommended for smooth operation |
| **Storage** | 1 GB base + ~1 GB for Ollama models (embedding + evaluator). ~2.