Building in the open

The roadmap.

Tau ships in small, documented phases — each one a readable slice of the agent, not a hidden branch. This page tracks what's shipped and what's next; the reasoning behind each phase lives in dev-notes/.

30 phases shipped
1 in progress
2 planned
01

the frontier

What's next

Phase 26

RPC support

Planned

Drive Tau as a subprocess over a structured RPC protocol, so other apps and editors can embed the agent without shelling out to the TUI.

Phase 27

Python SDK

Planned

A typed Python client for embedding Tau's harness and sessions directly in other Python programs, without going through the CLI.

Phase 21

Extensions

Up next

Local extension loading; extension-contributed tools, commands, prompt snippets/guidelines; event subscriptions.

02

shipped post-roadmap

Since then

Phase 25

System prompt display command

/system shows the effective system prompt Tau will send to the provider, without touching the transcript.

Phase 24

Session tree branching

A /tree modal for branching and revisiting session history, with branch summaries and tool-call filtering.

03

getting it right

Pre-extension polish

Phase 23

Advanced TUI and product polish

Richer transcript rendering, diff viewer, model/session picker UI, command palette, keybinding customization, theme polish.

Phase 22

Compaction and context management

Token/context estimation, manual /compact, automatic compaction threshold, compaction entries in the session tree.

Phase 20.4

Session visualization and export

Export a session transcript/tree, human-readable HTML view, preserved branch structure.

Phase 20.3

Skill invocation reliability

Loaded skills callable by default, manual /skill:<name> triggering, deterministic tests for skill delivery.

Phase 20.2

Thinking mode controls

Explicit thinking-mode model, TUI control with a Shift-Tab shortcut, active mode shown in the sidebar.

Phase 20.1

Accurate context accounting and sidebar refresh

Recalculate context/token usage after each turn and keep the TUI sidebar in sync.

04

before extensions

Hardening

Phase 20

Packaging and installation polish

Installable user-facing tool experience, uv tool/pipx docs, first-run setup docs, format docs.

Phase 19

Project context discovery and reload

Auto-discovery of AGENTS.md and instruction files, /context and /reload commands.

Phase 18

Provider configuration and setup

Durable provider config, multiple OpenAI-compatible providers, default provider/model, setup/login flow.

Phase 17.5

TUI transcript wrapping and resize behavior

Reflowed transcript text on resize, no horizontal scroll for normal messages, sane handling of long output.

Phase 17

TUI slash-command autocomplete

Autocomplete for commands, /skill:, and prompt templates with Tab/arrow-key selection.

Phase 16

Robust skills and prompt discovery

Load skills/prompts from Tau home, .agents, and project resources with deterministic precedence and diagnostics.

Phase 15

Slash command registry

Registry-based command handling shared by CLI/TUI, built-in commands, extension-ready internal API.

Phase 14

Session manager and resume

Create/list/resume sessions, session metadata index, tau sessions, tau resume <id>, TUI resume/new-session flow.

Phase 13

Tau home, paths, and automatic .agents resources

Canonical Tau home/resource paths, user-level and project-level .agents auto-loading, documented path precedence.

05

sessions & skills

A real coding agent

Phase 12

Textual TUI foundation

Textual app behind an adapter boundary, TUI state adapter, prompt input/transcript/status, basic commands and cancellation.

Phase 11

Print and event rendering modes

Final text mode, JSON event stream mode, transcript mode, renderer boundary in tau_coding.

Phase 10

System prompt assembly

Pi-style prompt builder, tool snippets/guidelines, skill index, project context, date/cwd suffix.

Phase 9

Skills and prompt templates

Markdown skills, markdown prompt templates, /skill:name expansion, resource path primitives.

Phase 8

Coding session wrapper

CodingSession, persistence around the harness, initial command seam, prompt expansion seam.

Phase 7

Session tree and JSONL persistence

Append-only session entries, JSONL storage, session replay, active leaf reconstruction.

06

the core loop

Foundation

Phase 6

Non-interactive print-mode CLI

Single prompt CLI, provider/model wiring, built-in tool registration.

Phase 5

Built-in coding tools

read, write, edit, bash — with per-tool prompt snippets and guidelines.

Phase 4

AgentHarness

Transcript owner, prompt()/continue_(), cancellation boundary.

Phase 3

Pure agent loop

Provider stream consumption, assistant message assembly, tool execution loop, agent events.

Phase 2

AI provider layer

Provider interface, fake provider for tests, OpenAI-compatible provider, environment-based API config.

Phase 1

Core types and event model

Provider-neutral messages, tool calls/results, agent events.

Phase 0

Project foundation and design docs

Package scaffold, docs and ADRs, test/lint/format/typecheck setup, basic `tau --version`.

τ

Roadmap phases turn into build journals under dev-notes/, then into these docs. Follow along or open an issue with ideas.