You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The OKF Agent Memory project provides an open, vendor-neutral, and domain-agnostic persistent memory layer for AI agents, built directly on Google's Open Knowledge Format (OKF) v0.2.1
Problem & Vision
Conversations with AI agents are temporary and ephemeral. When a context window resets or a new session starts, valuable discoveries, architectural decisions, and domain facts are lost unless stored systematically.2
Traditional solutions often rely on proprietary vector databases, locked memory APIs, or unstructured scratchpads. OKF Agent Memory solves this by treating an OKF knowledge bundle inside the repository (knowledge/) as the single source of persistent truth.
flowchart LR
A[AI Agent] -->|Reads / Queries| K[knowledge/ bundle<br/>OKF v0.2]
A -->|Discovers & Persists| K
H[Human Developer] -->|Inspects & Edits| K
Loading
Key Capabilities
Domain-Neutral: Functions equally well for software engineering, coaching, research, literature reviews, and operations.2
Core Value Proposition: Key differentiators and selling points detailed in value-proposition.
Deterministic Tooling & Separation of Concerns: Described in detail in architecture/layers.