OpenZync
Menu

Sign In

Graph Memory
for AI Agents

Open-source graph memory infrastructure for AI agents — with sub-50ms retrieval across 3 graph backends and 5 LLM providers. Build agents that remember.

Multi-Graph Backends
Enterprise Security
100% Open Source

What’s Next

Version support timeline — each release receives maintenance updates followed by extended security patches.

Maintenance SupportSecurity Support
Jul 2026
Oct 2026
Jan 2027
Apr 2027
Jul 2027
Oct 2027
Jan 2028
Apr 2028
v1.0
v1.1
v1.2
v2.0
v1.0.0rc2

OpenZync RC v1.0.0rc2

True feature-freeze — scoped project pins with org-isolated RLS, openai_like backends replacing OpenRouter, tombstone hard-retraction gate, and a production one-liner installer. SDK v1.0.0b5 + MCP v1.0.0b2 stay pinned. No further breaking changes before 1.0.0 stable.

OpenZync for

Built for developers who demand control.

OpenZync gives you a clean, typed API for graph memory across 3 backends. Integrate with your stack in minutes — Python SDK, REST API, and an MCP server for AI tool integration.

OpenZync by the Numbers

0
Graph Backends
PostgreSQL, FalkorDB, SurrealDB — all swappable
0
LLM Providers
OpenAI, Anthropic, Azure, OpenRouter, and Ollama
0
Core Contributors
Growing — join us on GitHubContribute
0
Latest Release
Beta — download from GitHubReleases

Supported Backends & Providers

OpenZync's graph memory infrastructure integrates with leading graph databases and LLM providers out of the box.

PostgreSQL
OpenAI
Anthropic
FalkorDB
Azure
Ollama
SurrealDB
OpenRouter
File-Preserving Memory

Memory that keeps the file.

Files attached to a session aren’t just digested to text and thrown away. Blobs are preserved as first-class, S3-backed objects that messages reference — and their content feeds a fact store where corrections supersede instead of piling up.

Preserved & referenced

Attachments are stored S3-backed as first-class session objects. Messages link to them via blob_id — the original file is never lost.

Supersede, not accumulate

Extracted content lands in the fact store, where later corrections supersede earlier facts — with effective-at reads and observable supersession events.

Ready to give your agents
graph-based persistent memory?

Open-source agent memory infrastructure. Start building in minutes. No credit card required.