riyogarta/syne
AI Agent Framework with Unlimited Memory — PostgreSQL-native, self-evolving, near-zero cost
Leverages pgvector semantic search with knowledge graph entity-relation traversal for unlimited memory recall, plus a 3-layer anti-hallucination filter that only persists user-confirmed facts. Built around an ability-based architecture allowing the agent to self-generate new capabilities, with all runtime behavior (soul, rules, identity, config) stored in PostgreSQL and modified via conversation—no config files. Integrates Google/OpenAI/Anthropic LLMs via OAuth or API keys, runs embedding and evaluation models locally on Ollama ($0), and supports distributed multi-node deployments via WebSocket with centralized Telegram bot control.
Stars
10
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/riyogarta/syne"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
topoteretes/cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory...
verygoodplugins/automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
CortexReach/memory-lancedb-pro
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder...
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot,...