docs

all articles

Sun, 04 Oct 2026

74 words / 0 links / 0 images / 0 snippets

The migration from Runtime-per-agent to OS-native ECS architecture is COMPLETE. ## Status All legacy Runtime code has been removed. The system now uses OS-native structures exclusively. ## Migration Complete - Phase 1 (Dual Mode): COMPL

Sun, 04 Oct 2026

agents-server: agents over HTTP

6514 words / 19 links / 1 images / 28 snippets

agents-server runs agents as a long-lived HTTP service. Sessions live in a SQLite database rather than in files, so a web application can start conversations, follow them live, complete deferred tool calls from its own workers, and pick s

Sun, 04 Oct 2026

Terminal UI (TUI)

2905 words / 2 links / 3 images / 42 snippets

The Terminal UI provides an interactive, real-time interface for agent conversations with support for multiple agents, streaming responses, visual feedback, file attachments, clipboard integration, subcall conversation visibility, and a tab

Sun, 04 Oct 2026

Analysis of Issue Dependencies and DAG-Aware Agent Processing

575 words / 0 links / 0 images / 0 snippets

Overview This document analyzes the current interaction between `sqq-agent.sh` and `create-issue.sh`, focusing on how issue dependencies are handled and the resulting impact on parallel development and git branch management. ## Current S

Sun, 04 Oct 2026

Tool System

3044 words / 7 links / 1 images / 108 snippets

The tool system provides agents with the ability to execute external commands, call APIs, and interact with other agents. Tools are dynamically registered and exposed to the LLM via the OpenAI function calling API. ## Overview ``` ┌──

Sun, 04 Oct 2026

OS Model Migration Guide

645 words / 3 links / 0 images / 34 snippets

Complete migration guide for transitioning from the legacy Runtime-based architecture to the new ECS-based OS Model. ## Overview The Agents framework has migrated from a Runtime-per-agent model to an Entity-Component-System (ECS) ar

Sun, 04 Oct 2026

OS Model API Reference

664 words / 9 links / 0 images / 44 snippets

Complete API reference for the Entity-Component-System (ECS) based OS architecture. ## Table of Contents 1. Core ECS Types 2. World Operations 3. Agent Operations 4. [Toolbox Oper

Sun, 04 Oct 2026

Durable Workflows How-To

1047 words / 7 links / 0 images / 22 snippets

This guide shows how to exercise and extend the durable-workflow features in agents-exe. Durable workflows let an agent turn pause after some tool calls, persist its state, and resume later when external results arrive. The canonical exam

Sun, 04 Oct 2026

Asynchronous Tool Calls

782 words / 2 links / 1 images / 7 snippets

By default an agent runs every tool call of a turn one after another and only answers the LLM once all of them are done. In asynchronous mode, calls run concurrently in the background, the LLM can be handed a partial answer while they run,

Sun, 04 Oct 2026

AI Assistant Guidelines - Agents Framework

549 words / 0 links / 0 images / 15 snippets

This document provides guidance for AI assistants (including future instances of myself) working on the Agents framework codebase. ## Quick Start for AI Assistants ### First Steps When invoked on this codebase, always: 1. **Check the knowle

Sun, 04 Oct 2026

SQQ Agent Flow Documentation

552 words / 0 links / 0 images / 8 snippets

Overview The `sqq-agent.sh` is a task queue automation system that manages AI agent execution on Git repositories. It integrates with GitHub issues, uses git worktrees for isolated task execution, and automatically creates pull requests

Sun, 04 Oct 2026

Adding New Executable-Program Tools

552 words / 0 links / 0 images / 9 snippets

Executable-program tools (also called "bash tools") are external programs that agents-exe can invoke as part of agent execution. These tools extend agent capabilities by performing side effects like reading files, installing packages, pro

Sun, 04 Oct 2026

Agents - AI Agent Framework

510 words / 14 links / 0 images / 9 snippets

A Haskell-based framework for building and orchestrating AI agents with support for multi-agent hierarchies, tool systems, and LLM integrations. ## Overview The Agents framework provides a complete infrastructure for: - Agent Definition

Sun, 04 Oct 2026

Export/Import

178 words / 0 links / 0 images / 5 snippets

Status: Removed The export and import commands have been removed from agents-exe. They were wonky and hard to use, so we’re taking another approach (see issue #339). ## Alternatives For sharing agents and tools, consider these alternati

Sun, 04 Oct 2026

MCP Protocol

466 words / 1 links / 0 images / 26 snippets

The Model Context Protocol (MCP) integration allows agents to connect to external servers that provide dynamic tool listings and execution capabilities. ## Overview MCP is a protocol for model context exchange that enables: - **Dynamic tool

Sun, 04 Oct 2026

CLI Reference

2181 words / 11 links / 0 images / 81 snippets

Complete reference for the Agents CLI commands and options. ## Global Options These options apply to all commands: bash agents-exe [GLOBAL_OPTS] COMMAND [COMMAND_OPTS] | Option | Default | Description | |––––|———|–––––

Sun, 04 Oct 2026

Internal Tool Mapping Documentation

631 words / 0 links / 0 images / 17 snippets

Overview This document describes how tools from various sources (OpenAPI, MCP, Bash, IO) are mapped to LLM-compatible tool names. This mapping is critical because different systems have different naming constraints. ## The Problem LLM AP

Sun, 04 Oct 2026

AI Context - Working on the Agents Framework

577 words / 0 links / 0 images / 19 snippets

READ THIS FIRST when invoked on this codebase. ## Immediate First Steps When you’re invoked on this project, run these queries immediately: ```sql – 1. What is this project? SELECT * FROM project_overview; – 2. What docs exist? SELE

Sun, 04 Oct 2026

Changelog: OS Model Migration

405 words / 0 links / 0 images / 3 snippets

Date: March 2026 Commits: 0eb5263 to cb52af7 ## Summary This release introduces a major architectural refactoring of the agents-exe core, migrating from a Runtime-per-agent model to a centralized **Entity-Component-System (ECS)

Sun, 04 Oct 2026

Architecture

1409 words / 0 links / 1 images / 13 snippets

This document describes the runtime architecture and core components of the Agents framework. ## Core Architecture The framework is built around a layered architecture that separates concerns between agent definition, runtime execution, and

Sun, 04 Oct 2026

Session Management

1019 words / 0 links / 1 images / 49 snippets

Session management provides persistent storage and retrieval of agent conversations, enabling conversation resumption, history analysis, and multi-modal content support. Sessions can now be stored across multiple locations with a unified re

Sun, 04 Oct 2026

Parameters, bindings, and narrowing sub-agents

1549 words / 13 links / 0 images / 10 snippets

Most agent frameworks give a tool’s arguments to the model in full, or hide them entirely behind a wrapper script the author has to hand-maintain. This feature gives you a middle ground with no code: an agent’s author declares a handful of

Sun, 04 Oct 2026

Advanced Configuration

1097 words / 13 links / 0 images / 27 snippets

This guide covers advanced configuration patterns for agents-exe, including recursive agent references, mutual recursion, and runtime safety controls. ## Table of Contents - Recursive Agent References - [Self-

Sun, 04 Oct 2026

Agent templates

714 words / 11 links / 0 images / 7 snippets

An agent file can be a tramaj program instead of JSON. The program is evaluated once, when the agent is loaded, and must produce the JSON an agent file holds. From there on nothing changes: the va

Sun, 04 Oct 2026

File Loader

289 words / 0 links / 0 images / 25 snippets

The file loader utilities provide JSON file loading, section-based file parsing, and directory scanning for agent configurations and tools. ## Overview ``` ┌───────────────────────────

Sun, 04 Oct 2026

Iterative Development Workflow

776 words / 1 links / 0 images / 15 snippets

How to handle multi-step, recursive, or iterative invocations on this codebase. ## Invocation Patterns ### Pattern 1: Fresh Start (No Previous State) When: First time working on this codebase, or no knowledge base. Steps: 1. Initi

Fri, 25 Sep 2026

Docs

299 words / 30 links / 1 images / 0 snippets

The guides and references, mirrored from the repository’s documentation/ directory: architecture, tools, the server, sessions, the TUI, parameters, and the migration and workflow notes.

other topics