Features

Everything you need.
Nothing you don't.

Core capabilities are built in from the OMP mainline; advanced content is ported from Pi's semantic source. Extensions cover the rest — build what you want, install what you don't want to build.

01

Core capabilities

Built-in defaults, not optional extensions.
01

SSubagents

Split work across parallel subagents, each with its own context and toolset. Results aggregate back into the main session.

02

PPlan mode

Plan before you act: the agent produces a plan for your review, then touches the workspace only after approval.

03

LLSP language services

Built-in LSP client: go-to-definition, find references, diagnostics, and completions — code semantics at edit time.

04

DDAP debug adapter

Speaks the Debug Adapter Protocol: set breakpoints, read stack frames, inspect variables, and explain failures.

05

HHindsight memory

Lessons and outcomes from past sessions are revisited and applied automatically in later tasks.

06

EHashline edits

Line-precise, content-addressed editing semantics: refactors and bulk replacements stay traceable.

07

TTime-traveling rules

Project rules that apply per time slice: old commit conventions don't leak onto new code.

08

RNative Rust engine

Text, regex, grep, and diff heavy lifting on Rust primitives — large files and big repos stay fast.

09

TProject tracking docs

A long-term tracking system independent of memory: activate with /tracking, the AI writes milestones and key decisions into .zeta/tracking/, survives across sessions, visualized in the desktop Tracking panel.

10

ZZH/EN UI switch

/language zh toggles the CLI and command-description language; the setting persists.

11

WDesktop default workspace

The desktop app ships a global default workspace (~/.zeta/workspace) — ready to use without picking a directory first.

12

CClear config paths

Project-level .zeta/ and user-level ~/.zeta/ (same location on Linux and Windows — under the home directory): config, memory, tracking, and logs each in their place.

02

Context engineering

Control what enters the context window and how it is managed — don't let the model guess.
01

AGENTS.md

Project instructions loaded at startup from ~/.zeta/agent/, parent directories, and the current directory.

02

SYSTEM.md

Replace or append the default system prompt per project — a persona and constraints for each repository.

03

Skills

Capability packages loaded on demand: instructions plus tools, with progressive disclosure that doesn't bust prompt caches.

04

Prompt templates

Reusable Markdown prompts, expanded with /name.

05

Auto compaction

Older messages are summarized near the context limit; strategy is fully customizable via extensions.

06

Dynamic context

Extensions inject messages before each turn, filter history, implement RAG, or build long-term memory.

03

Sessions: a tree, not a log

Return to any previous node and continue; branches and mainline live in one file.
01

Branching history

Sessions are stored as trees. Navigate to any earlier point and continue from there.

02

Export & share

/export produces HTML; /share uploads to a shareable URL anyone can open.

03

Encrypted collab

/collab opens an end-to-end encrypted live session — participants render the same session and tool cards.

04

Resume anywhere

Restart with --continue to re-enter the same session with full reasoning and decisions intact.

04

Four modes

One agent, many interfaces.
Interactive

The full TUI: panels, previews, tool cards, keybindings.

Print / JSON

zeta -p "query" for scripts; --mode json streams events for consumers.

RPC

JSON protocol over stdin/stdout for non-Node integrations.

SDK

Embed as a library in your own application, with full control over the agent lifecycle.

05

Primitives, not features

Features other agents bake in, you can build yourself. Extensions are TypeScript modules with access to tools, commands, keybindings, events, and the full TUI.
01

Permission gates

Custom confirmation flows — allow or block sensitive operations per your environment and security needs.

02

Path protection

Declare protected paths; the agent's reads and writes stay inside the allowed region.

03

MCP integration

Connect MCP servers via extensions, or build CLI tools with READMEs as skills.

04

Sandboxed execution

Run commands inside a container or sandbox, isolating risk from the agent.

05

Extension discovery

skills, hooks, tools, commands, rules, prompts, and .mcp.json all discovered from extensions.

06

50+ examples

Subagents, plan mode, SSH execution, custom editors, status bars, overlays — official examples ready to use.