zavora-cli

  ███████╗ █████╗ ██╗   ██╗ ██████╗ ██████╗  █████╗
  ╚══███╔╝██╔══██╗██║   ██║██╔═══██╗██╔══██╗██╔══██╗
    ███╔╝ ███████║██║   ██║██║   ██║██████╔╝███████║
   ███╔╝  ██╔══██║╚██╗ ██╔╝██║   ██║██╔══██╗██╔══██║
  ███████╗██║  ██║ ╚████╔╝ ╚██████╔╝██║  ██║██║  ██║
  ╚══════╝╚═╝  ╚═╝  ╚═══╝  ╚═════╝ ╚═╝  ╚═╝╚═╝  ╚═╝

Your AI agent, in the terminal. Built on ADK-Rust.

Multi-agent orchestration, tool safety controls, streaming markdown, checkpoints, MCP integration — all from a single binary.

Install

cargo install zavora-cli

Or build from source:

git clone https://github.com/zavora-ai/zavora-cli.git
cd zavora-cli
cargo install --path .

Requires Rust 1.85+ (rustup, cargo).

Quick Start

1. Export an API key for any supported provider:

export OPENAI_API_KEY="sk-..."
# or: GOOGLE_API_KEY, ANTHROPIC_API_KEY, DEEPSEEK_API_KEY, GROQ_API_KEY

Or use Ollama locally with no key needed:

OLLAMA_HOST=http://localhost:11434  # optional, this is the default

2. Start chatting:

zavora-cli chat

Usage

# Ask a one-shot question
zavora-cli ask "Explain Rust ownership"

# Interactive chat with a specific model
zavora-cli --provider openai --model gpt-4.1 chat

# Workflows
zavora-cli workflow sequential "Plan an MVP rollout"
zavora-cli workflow graph "Draft a release plan with risks"

# Health check
zavora-cli doctor

Multi-Agent Orchestration

The assistant automatically delegates to specialist sub-agents when appropriate:

• git agent — git operations, commits, branch management
• research agent — codebase exploration, file search, analysis
• planner agent — task breakdown, todo lists, project planning

Transfers are visible in the UI with → agent_name indicators. Tool calls show as ⚡ tool_name.

Chat Commands

Built-in Tools

Context Management

• /usage shows real-time token breakdown by author (user, assistant, tool, system)
• Prompt shows ⚠ (>75%) or 🔴 (>90%) when approaching context limits
• /compact manually summarizes history to reclaim space
• Auto-compaction triggers when configured thresholds are exceeded

Configuration

Runtime defaults live in .zavora/config.toml:

[profiles.default]
provider = "openai"
model = "gpt-4.1"
session_backend = "sqlite"
session_db_url = "sqlite://.zavora/sessions.db"
retrieval_backend = "disabled"
tool_confirmation_mode = "mcp-only"
compaction_threshold = 0.75
compaction_target = 0.50
telemetry_enabled = true

zavora-cli profiles list
zavora-cli --profile ops profiles show

Agent Catalogs

Configure agent personas separately from profiles. Precedence: implicit default → global ~/.zavora/agents.toml → local .zavora/agents.toml.

[agents.coder]
description = "Code-focused assistant"
provider = "openai"
model = "gpt-4.1"
tool_confirmation_mode = "always"
allow_tools = ["fs_read", "fs_write", "execute_bash"]

zavora-cli agents list
zavora-cli --agent reviewer ask "Review this patch"

Advanced Features

Tool Policy and Hooks

[profiles.default]
tool_confirmation_mode = "mcp-only"  # never | mcp-only | always
tool_timeout_secs = 45
tool_retry_attempts = 2

[[profiles.default.hooks.pre_tool]]
name = "block-rm"
match_tool = "execute_bash"
match_args = "rm -rf"
action = "block"
message = "Destructive rm blocked by hook policy"

MCP Integration

[[profiles.ops.mcp_servers]]
name = "ops-tools"
endpoint = "https://mcp.example.com/ops"
enabled = true
timeout_secs = 15
auth_bearer_env = "OPS_MCP_TOKEN"
tool_allowlist = ["search_incidents", "get_runbook"]

Guardrails

Independent input/output content policy (disabled | observe | block | redact):

zavora-cli --guardrail-input-mode block --guardrail-output-mode redact ask "Summarize this"

Retrieval

zavora-cli --retrieval-backend local --retrieval-doc-path ./docs/knowledge.md ask "What are our standards?"

Server Mode and A2A

zavora-cli server serve --host 127.0.0.1 --port 8787

Endpoints: GET /healthz, POST /v1/ask, POST /v1/a2a/ping.

Development

make fmt          # format
make check        # cargo check
make lint         # clippy
make test         # unit tests
make ci           # full CI pipeline

License

MIT