SQLite for Agent Memory: Building AKG, an Open Knowledge Graph File Format

Learn about AKG, an open knowledge graph format for agent memory inspired by SQLite. Explore its binary structure, SDKs, and how it enables real-time opponent profiling in poker.

GPT-5 Claude Code Gemini 3 Go TypeScript

Overview

Agent Knowledge Graph (AKG) is an open binary file format for agent memory that borrows inspiration from SQLite, but the data model is a knowledge graph instead of tables. It is meant to integrate seamlessly into existing agent implementations using SDKs for Go and TypeScript, with support for Python and Rust coming soon. To stress test the format and SDK I built a headless Texas Hold’em harness where agents play poker against each other using various memory strategies. For the demo I will discuss a bit about the philosophy behind the project, walk through the raw .akg binary format, show the TypeScript/Go SDKs, and share the JSONL data stream of an AKG-backed agent building a psychological profile of its opponents in real-time.

Links

https://github.com/RobertGumeny/akg
AKG is a single-writer binary file format and SDK.
https://github.com/RobertGumeny/doug
Doug provides precompiled CLI binaries for macOS and Linux installation.

Tech stack

GPT-5

OpenAI's GPT-5: The unified, multimodal foundation model delivering PhD-level reasoning and state-of-the-art coding performance.

Copy that: GPT-5 is OpenAI's flagship multimodal model, launched August 7, 2025, as the successor to GPT-4. This is a major architectural shift: it unifies advanced reasoning capabilities (like the 'o-series' models) and rapid response times into a single system, eliminating the need for manual model switching (Source: OpenAI, August 2025). The model demonstrates state-of-the-art performance across technical benchmarks (math, programming, finance) and features a massive 272,000-token context window (Source: Jagran Josh, Voiceflow). Developers access it via the API in variants—including `gpt-5-mini` and `gpt-5-nano`—optimized for latency and cost trade-offs, making this frontier intelligence accessible across all ChatGPT tiers (Source: Botpress, Jagran Josh, Voiceflow).

https://openai.com/gpt-5

View projects
Claude Code

Anthropic's agentic coding tool: Unleash Claude's raw power directly in your terminal or IDE to turn complex, hours-long workflows into a single command.

Claude Code is Anthropic’s powerful agentic coding assistant, designed for high-velocity development. It operates natively within your terminal, IDE (VS Code, JetBrains), or via a web interface, allowing you to delegate complex tasks like feature building, bug fixing, and codebase navigation. The agent plans, edits files, executes commands, and creates commits, maintaining awareness of your entire project structure. Internally, Anthropic engineers using Claude Code reported a 67% increase in productivity, demonstrating its capacity to deliver significant gains for Pro and Max plan users.

https://claude.com/code

View projects
Gemini 3

Gemini 3 Pro: Google's most intelligent, state-of-the-art multimodal AI model, engineered for advanced reasoning and complex agentic coding workflows.

This is the third-generation model, the new intelligence foundation for Google's ecosystem. Gemini 3 Pro delivers state-of-the-art reasoning and world-leading multimodal understanding: it seamlessly processes text, images, video, audio, and code. It is our most powerful agentic and vibe-coding model yet, designed to handle long-horizon, multi-step tasks; it features an industry-leading 1 million token context window. The model's performance is validated by its breakthrough score of 1501 Elo on the LMArena Leaderboard, confirming its superior capability for developers building on platforms like Vertex AI and the new Google Antigravity.

https://ai.google.dev/gemini/models/gemini-3

View projects
Go

Go is Google's open-source, compiled, and statically-typed language built for high-performance, scalable systems (microservices, cloud infrastructure) via simple, efficient concurrency (goroutines).

Go (often called Golang) is a compiled, open-source language designed at Google by Robert Griesemer, Rob Pike, and Ken Thompson to solve modern software challenges: slow build times and complex dependencies. It is statically-typed and syntactically clean, drawing inspiration from C but adding key features like automatic garbage collection and a powerful, built-in concurrency model (goroutines and channels). This design delivers fast compilation and runtime efficiency, making it the premier choice for building scalable, reliable systems; major projects like Docker and Kubernetes rely on Go for their core infrastructure.

https://go.dev/

View projects
TypeScript

TypeScript is an open-source superset of JavaScript: it adds static typing and compiles to clean, standards-based JavaScript.

TypeScript is a high-level, open-source language developed by Microsoft: it acts as a superset of JavaScript, adding a powerful static type system. This system enables compile-time type checking, catching errors before runtime (a critical benefit for large-scale applications). The TypeScript Compiler (TSC) reliably transpiles all code into clean, standards-based JavaScript (ES3 or newer), ensuring compatibility across any browser or host environment (Node.js, React.js, etc.).

https://www.typescriptlang.org/

View projects

SQLite for Agent Memory: Building AKG, an Open Knowledge Graph File Format

Related talks