{"slug": "learn-how-coding-agents-are-built", "title": "Learn how coding agents are built", "summary": "Tau is an educational Python coding agent designed to teach how agents are built by exposing every component—provider adapters, harness, coding environment, and terminal UI—in readable layers. The project emphasizes a clean separation between the reusable harness, environment, and UI, allowing developers to study and build their own agents step by step.", "body_md": "An educational coding-agent project\n\n**Tau** is a small Python coding agent you read like a\ntextbook. Watch it stream model output, call tools, manage sessions,\nand grow into a terminal UI — one readable layer at a time.\n\nNo hidden machinery. Every moving part is on the page.\n\nProvider adapters turn model responses into provider-neutral events the rest of the agent consumes.\n\nThe reusable harness: messages, tools, transcript state, cancellation, queued prompts, sessions.\n\nThe coding environment: files, shell, durable sessions, skills, slash commands, and a Textual TUI.\n\nThe lesson\n\nTau answers the questions tutorials skip: What *is* an agent loop? Where do tool calls come from? How does the transcript grow? How do sessions survive the process exiting?\n\nThe core idea\n\nThe whole lesson is the boundary. A reusable harness must not depend on the terminal, file paths, or Rich rendering. Those wrap the harness — they never live inside it.\n\n`~/.tau/sessions`\n\nOne job per package. Study the provider layer, harness, and coding app on their own.\n\nThe agent emits a stream you can render, test, and export — not control flow buried in callbacks.\n\nEducational, not a toy. Run it as a real terminal agent while reading the code behind it.\n\nBuilt phase by phase, each with notes on what was added, why, and how it fits.\n\nThe inspiration\n\nTau borrows Pi's architectural lesson — keep the harness, the environment, and the UI apart. Not a line-by-line port; an educational Python take on the same core ideas.\n\nA map for building your own agent: start with events, add a loop, wrap it in a harness, then give it tools and a UI.", "url": "https://wpnews.pro/news/learn-how-coding-agents-are-built", "canonical_source": "https://twotimespi.dev/", "published_at": "2026-06-29 02:59:36+00:00", "updated_at": "2026-06-29 03:27:44.840491+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "machine-learning", "large-language-models", "generative-ai"], "entities": ["Tau", "Python", "Textual", "Pi"], "alternates": {"html": "https://wpnews.pro/news/learn-how-coding-agents-are-built", "markdown": "https://wpnews.pro/news/learn-how-coding-agents-are-built.md", "text": "https://wpnews.pro/news/learn-how-coding-agents-are-built.txt", "jsonld": "https://wpnews.pro/news/learn-how-coding-agents-are-built.jsonld"}}