Banner

Agent Space Directory

Project: agentspace.directory is an open-source framework and discovery hub for LLM-agnostic, file-based AI agents. Built on the principle of Single-Source-of-Truth (SSoT), it allows developers to declare an agent's entire "soul"—its identity, logic, memory, and activity—within a single, portable directory of Markdown files.

By treating the file system as the primary orchestration layer, agentspace.directory eliminates fragmented configurations and provides a transparent, version-controlled environment where agents can be developed, tested, and shared regardless of the underlying language model.

Unified Directory Pattern Single-Source-of-Truth

🤖 Engine Agnostic Display

The entire agent behavior is declared in one single directory. It can be run seamlessly by different engines:

GPT Claude Gemini

1. Core Concept & Structure

The website facilitates a "Directory-First" approach to AI. All agent logic is declared in a single, LLM-agnostic folder structure.

icon

instructions.md

The "DNA" of the agent—system roles and logic.

icon

memories.md

Shared long-term context and personal facts.

icon

tools.md

Unified API and capability definitions.

icon

tracks/

A subfolder for active state tracking (e.g., debug-xxx.md, feat-xxx.md).

2. Integrated Extensions

icon

Extension A: apitests (apitests)

Purpose: TDD for agents.

Implementation: gentests are created within individual project repositories.

Gemini Instruction: When working on a task in a tracks/ file, Gemini must first check the project repo for gentests and run them to verify any logic changes.

icon

Extension B: apistubs (apistubs)

Purpose: Environment isolation and safety.

Implementation: Used to mock unstable or expensive third-party APIs.

Gemini Instruction: If a task requires an external API that isn't available in the cloud VM, Gemini should use apistubs to create a mock endpoint based on the schema in tools.md.

3. Directory Examples (Use Cases)

icon

Example 1: Test & Dev Agent

Focus: Automated debugging and feature implementation.

Workflow: Reads a bug report in tracks/, identifies the failing apitest in the repo, and fixes the code until the test passes.

Highlight: This workflow heavily leverages the apitests extension (apitests) to practice Test-Driven Development (TDD) for agents, ensuring robust logic changes through automated gentests!

icon

Example 2: Procurement Agent

Focus: Business process automation and governance.

Workflow: Uses instructions.md to vet vendors against budget rules. Uses apistubs to simulate a payment gateway response before finalizing a purchase "track."

icon

Example 3: Second Brain & Personal Planner

Focus: Knowledge synthesis and schedule optimization.

Workflow: Declares personal events (e.g., "Kate's Birthday March 19") in memories.md. The agent proactively creates a tracks/ file to plan the event 14 days in advance.