Zelari Code

             -#%=
           .*%%%@#:
          =%%%%%%%@*
         +%%%%%%%%%%#.
        +%%%@@@@@@@%@#.
      .*%@@@@@@@@@@@@@%-
     .#%@@@@@@@@@@@@@@@@-
     *%@@@@@@@@@@@@@@@@@%.
    :@%%@@@@@@%:+%@@@@@%@=
     =@%%@@@@@%.=-+%@%%@*
     .=@@%@@@@%.*@*-+@@*.
   -*%@@@@@@@@%.*@@@+:#@@#=.
  *%%%%%%@@@@@@.*#%#=-:+@@@%
 :@%%%%%%@@@@@@.:=.*:*@@@@@@=
 *@%%@%%@@@@@@@*%@*:-:%@@@@@%.
:@@@%@@@@@@@@@@@@@@#%@@@@@@@@=
*%%%%%%%%%%%%%%%%%%%%%%%%%%%%#

     Z E L A R I   C O D E
          N-THEM Studio

AI Council coding agent CLI — multi-agent orchestration with slash commands, provider-agnostic LLM streaming, and self-update.

📖 Guida completa all'uso (IT) — installazione, TUI, comandi slash, council, skills, workspace, headless, MCP.

Zelari Code is a standalone CLI extracted from AnathemaBrain. It brings the multi-agent council (Caronte, Nettuno, Gerione, Plutone, Minosse, Lucifero) directly into your terminal with a rich TUI (Ink + React), slash command system, and provider-agnostic LLM streaming (OpenAI-compatible, xAI Grok with OAuth, GLM/Z.AI).

Upgrading from ≤ 0.4.x? See MIGRATION.md — the internal src/main/core/, src/agents/, src/shared/, src/types/ paths no longer exist. The published core package is @zelari/core (MIT). 9 subpath exports.

Prerequisites

Optional (for v1.3.0 advanced tools)

These are opt-in — the CLI runs fine without them. The agent auto-skips a tool if its dependency is missing.

Disable any tool group: set ZELARI_LSP=0, ZELARI_AST=0, ZELARI_SEMANTIC=0, ZELARI_BROWSER=0, ZELARI_DIAGNOSTICS=0.

Install

npm install -g zelari-code
zelari-code

Prerequisites:

• Node.js ≥ 20 — required. Without it the agent cannot run npm/tsc/builds, so zelari-code refuses to boot.
• Git — recommended. Without it, /diff, /undo and the git sidebar are disabled. Install from https://git-scm.com.
• Git Bash (Windows only) — recommended. The agent's bash tool needs real POSIX semantics (ls, which, $VAR, &&). Ships with Git for Windows.

After install, verify your environment:

zelari-code --doctor   # checks shim, bundle, PATH, node/git/bash in the agent shell

Why --doctor matters on Windows: the agent runs commands through Git Bash, which inherits a different PATH than the Node process. Node can be visible to PowerShell yet invisible to Git Bash (typical when Node was installed for "current user" only). --doctor's node (agent shell) row catches this; the boot-time preflight (runPreflight) blocks the launch with an actionable message instead of letting the agent fail mid-task.

zelari-code: command not found (Windows)

After npm install -g, the zelari-code command may not be on your PATH. Fix:

PowerShell (run as admin, then restart your terminal):

$npmPrefix = npm config get prefix
[Environment]::SetEnvironmentVariable("Path", $env:Path + ";$npmPrefix", "User")

Git Bash / WSL:

echo 'export PATH="$(npm config get prefix):$PATH"' >> ~/.bashrc
source ~/.bashrc

Verify the fix: where zelari-code (CMD) or which zelari-code (Bash) should print a path.

Node visible to PowerShell but not to Git Bash? This is the dual-PATH problem: Node installed for "current user" only reaches the user shell, while Git Bash inherits the system Path. Fix: reinstall Node with "Add to PATH for all users", or add C:\Program Files\nodejs\ to the System Path (not User). Confirm with zelari-code --doctor — the node (agent shell) row must read OK.

First Run

The first time you run zelari-code (or whenever your provider config is missing), the CLI launches a 5-step onboarding wizard instead of the regular TUI:

╭─────────────────────────────────────────────────╮
│ zelari-code v1.3.0 — first-time setup    │
│ 1/welcome  2/provider  3/model  4/apikey  5/...│
│                                                 │
│ Welcome! Let's get you coding in under 2 min.   │
│ Press [Enter] to continue, [Q] to quit.         │
╰─────────────────────────────────────────────────╯

The wizard walks you through:

1. Welcome — overview + how to quit.
2. Provider — pick from grok, minimax, glm, deepseek, openai-compatible (↑/↓ + Enter).
3. Model — type a model name or accept the default (Enter).
4. API key — choose env (use GROK_API_KEY etc.), keystore (save locally), or skip (set later via /login).
5. Confirm — review + Enter to commit.

When you press Enter on confirm, the wizard writes ~/.tmp/zelari-code/provider.json (and keys.json if you chose keystore), shows a brief "✓ Setup complete!" banner, then transparently transitions into the regular TUI — no need to re-launch.

Skipping / re-running

zelari-code --no-wizard            # skip wizard even on first run
zelari-code --reset-config         # force re-run wizard (clears provider.json)
ZELARI_NO_WIZARD=1 zelari-code     # env equivalent of --no-wizard
zelari-code --version              # print version + exit (no TUI)
zelari-code --help                 # print help + exit (no TUI)

The wizard re-runs automatically if provider.json is missing on the next launch.

Quick Start

# Set your OpenAI-compatible API key (OpenAI, Together, Groq, custom endpoint, etc.)
export OPENAI_API_KEY=sk-...

# Or use Grok via OAuth (Device Authorization Grant — RFC 8628)
zelari-code
# Inside the TUI: /login grok
# → A code + verification URL appears; open the URL, enter the code, authorize.

# Or use GLM/Z.AI
export GLM_API_KEY=...

# Run zelari-code from any directory
zelari-code

Slash Commands

Full reference: docs/GUIDA.md (all flags, examples, skill IDs).

TUI: shift+tab cycles agent → council → zelari mode for free-form prompts (with terminal-fallback hardening since v1.3.0). The equivalent command /mode [agent|council|zelari] works in any terminal.

Headless Mode

Run a single task without the TUI (CI/scripts):

zelari-code --headless --task "Explain src/cli/main.ts" --output plain
zelari-code --headless --task "Design a REST API" --council --output json

See docs/GUIDA.md for exit codes and all flags.

Self-Update

Zelari Code includes a built-in update mechanism:

# Inside the TUI:
/update          # check for updates (prints current vs latest)
/update --yes    # apply update (runs npm install -g zelari-code@latest)

On startup, the CLI silently checks the npm registry. If a newer version is available, it prints a one-line hint to stderr.

Disable auto-check: ANATHEMA_DEV=1 zelari-code

Features

• 🤖 Multi-agent council — 6 roles (Caronte, Nettuno, Gerione, Plutone, Minosse, Lucifero) with feedback loops and member promotion
• ⚡ Zelari-mode — autonomous multi-run missions: a free-form prompt is turned into a structured mission brief, then the council loops (design → implementation) until the MVP slice's completion.ok is green or the iteration budget runs out
• 🧠 Project memory — zero-dependency file-based recall (.zelari/memory/), fed into the council as RAG context between mission slices (opt-out with ZELARI_MEMORY=0)
• ⇧⇥ Agent/council/zelari mode switch — shift+tab cycles free-form prompts between the single agent, the full council pipeline, and an autonomous mission (mode shown in the status line)
• 🎨 Rich TUI — Ink + React: native-scrollback chat stream, input bar with status line below it (mode · provider · model · session · cwd · execution timer)
• 🗂️ Live git sidebar — right-hand panel with the N-THEM emblem and the working-tree changes (+added/-removed per file, refreshed every 4s; auto-hidden on narrow terminals)
• ⏱️ Execution timer — elapsed time of the in-flight turn in the status line (⏱ 12s), frozen as last 34s when the run completes
• 🧠 Provider-agnostic — OpenAI-compatible APIs (OpenAI, Together, Groq, custom), xAI Grok with OAuth refresh, GLM/Z.AI
• 🛠️ Built-in tools — filesystem (read/write/edit), shell (bash), search (grep), web fetch/search
• 🧠 LSP code intelligence (lsp_* tools) — go-to-definition, find references, hover type, document symbols, rename symbol via real language servers (tsserver, pyright, …)
• 🌲 AST structural tools (ast_* tools) — symbol outline + find-by-name via the TypeScript compiler API, no language server needed
• 🔎 Semantic search (semantic_search + /index) — concept-level code search via embeddings, local-first
• 🌐 Browser verification (browser_check) — headless browser with click/fill/goto/wait actions, console + network + screenshot capture for visual verification of web work
• 🔁 Post-edit diagnostics loop — after every edit_file/write_file the harness runs project lint/compile (eslint, ruff, LSP-pluggable) and surfaces the errors to the model in the same turn (opt out: ZELARI_DIAGNOSTICS=0)
• 💾 Prompt-cache accounting — tracks prompt-cache hit rate per provider/model and surfaces it in the status bar (cache 73%) so you can see when a session is amortizing its prefix
• 🧷 Workspace checkpoints — /checkpoint [label] + /rollback [id|latest] use git plumbing to snapshot the working tree (tracked + untracked) and restore it atomically; every zelari-mode mission takes one before starting
• 🤝 Sub-agent delegation (task tool) — delegate a focused read-only research sub-task to an isolated sub-agent with its own fresh context, max 12 tool turns, no write/bash/recursion
• 📚 23 coding skills (+ user SKILL.md from .zelari/skills/, .claude/skills/, …)
• 🔄 Cross-provider failover — automatic retry with provider swap on transient errors
• 📊 Metrics + skill history — fire-and-forget logging to ~/.tmp/zelari-code/
• 🗜️ Session management — JSONL transcripts, resume across restarts, compaction
• 🌿 Branch isolation — session snapshots per branch
• 🔌 MCP — external MCP servers via .zelari/mcp.json
• 🆕 Self-update — /update slash command + silent registry check on startup

Architecture

zelari-code (CLI, proprietary)
├── src/cli/                  # Ink TUI, provider config, workspace, wizard, MCP
│   ├── components/           # ChatStream, InputBar, Sidebar, StatusBar, …
│   ├── slashHandlers/        # /provider, /workspace, /update, …
│   └── workspace/            # .zelari/ persistence + AGENTS.MD curation
└── packages/core/            # @zelari/core (MIT, npm)
    ├── core/                 # AgentHarness — provider-neutral agent loop
    ├── agents/               # Council API, roles, 23 skills, tool schemas
    ├── harness/tools/        # Tool registry + filesystem/shell/search/web
    ├── events/               # BrainEvent contract
    └── council/              # Run mode, tier banners

AgentHarness takes (model, provider, messages, tools) + a streaming function and yields AsyncIterable<BrainEvent>. The CLI subscribes and renders via eventsToMessages(). See MIGRATION.md for the v0.5+ package boundary.

Environment Variables

See docs/GUIDA.md for the full list.

Council Workspace

The CLI persists council output (decisions, risks, docs, plan, reviews) into a project-local .zelari/ directory and auto-curates an AGENTS.MD at the project root.

Layout

.zelari/                      # auto-gitignored, per-project
├── plan.md                   # phases / tasks / milestones (Markdown + YAML frontmatter)
├── risks.md                  # risk register (live, ordered by severity)
├── decisions/                # ADRs (Architecture Decision Records) — 001-<slug>.md
├── reviews/                  # Minosse verdict per council run
└── docs/                     # doc drafts produced by the council
AGENTS.MD                     # committed at project root, auto-curated from .zelari/

Slash commands

AGENTS.MD format

AGENTS.MD is partitioned into:

1. Manual blocks (free-form, preserved verbatim across updates) — write anything you want here.
2. Auto-managed sections delimited by <!-- zelari:auto:start section="..." --> / <!-- zelari:auto:end --> markers — overwritten each sync.

Auto-managed sections:

• tech-stack — languages, frameworks, build tools (derived from package.json)
• decisions — accepted ADRs (newest first, capped)
• conventions — code conventions observed in source tree
• build — build/test/lint commands
• open-questions — info-level risks + unsolved questions

Set ZELARI_AGENTS_MD=0 to disable AGENTS.MD auto-curation.

Storage layout internals

• Frontmatter: subset YAML (scalars, flow/sequence/block-sequence arrays, flow/block maps) — no external deps.
• Concurrency: per-key mutex (filesystem writes are serialized per artifact).
• Idempotency: hash comparison — AGENTS.MD write is skipped when no section changed (clean git diff).

See docs/plans/2026-07-01-council-workspace-cli-stubs.md for the full schema.

Documentation

Development

git clone https://github.com/N-THEM-Studio/zelari-code.git
cd zelari-code
npm install
npm run build:cli
npm link
zelari-code

Run tests

npm test

Typecheck

npm run typecheck

Related Projects

• AnathemaBrain — the Electron desktop GUI that shares the agent runtime + council system with this CLI
• Zelari Coder originated as the npm run coder script inside AnathemaBrain
• @zelari/core on npm — reusable agent runtime (MIT)

License

Proprietary © 2026 N-THEM Studio. See LICENSE.