VeilCLI

Enterprise autonomous agent runtime — local, API-first, multi-model.

VeilCLI lets you define AI agents as simple files, run them as a local REST server, and control them through a clean HTTP API or interactive CLI. Agents can chat, run multi-step tool work inside a turn, spawn sub-agents, and maintain persistent memory — all without external services.

Key Features

• Chat agents + sub-agents — converse with agents and spawn sub-agents via agent_spawn
• 24 built-in tools — bash, file I/O, web search/fetch, memory, multi-agent communication, todos, and more
• Persistent memory — per-agent and project-wide Markdown memory files
• Multi-agent orchestration — parallel fan-out, durable subscriptions, sync/async spawning
• Layered config — global → project → local → CLI flags
• Multi-provider routing — configure multiple providers (OpenRouter, Anthropic, Claude CLI, Ollama, etc.) and route models per role
• Any OpenAI-compatible LLM — OpenRouter, local Ollama, Azure, etc.
• Zero external dependencies — SQLite storage, native fetch, Node.js only

Requirements

• Node.js ≥ 20.0.0
• An OpenAI-compatible API key (e.g. OpenRouter)

Installation

npm install -g @newsails/veil-cli

Quick Start

# 1. Set up a workspace
mkdir my-workspace && cd my-workspace

# 2. Save your API key (Optional)
veil login --key sk-or-v1-...

# 3. Start the server
veil start

# 4. Chat with the default agent
curl -X POST http://localhost:5050/agents/hello/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello!"}'

# 5. Chat with tools
curl -X POST http://localhost:5050/agents/assistant/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "List all .js files in the current directory"}'

→ See docs/guide/01-quickstart.md for the full walkthrough.

Documentation

API Reference

| Doc | Contents | |-----|----------| | docs/api/README.md | Overview, auth, error codes | | docs/api/01-system.md | /health, /status, /shutdown | | docs/api/02-agents.md | List and inspect agents | | docs/api/03-chat.md | Chat endpoint, multi-turn sessions | | docs/api/05-sessions.md | Session management and messages |

Project Guide

| Doc | Contents | |-----|----------| | docs/guide/README.md | Guide index | | docs/guide/01-quickstart.md | Install, first agent, first request | | docs/guide/02-folder-structure.md | .veil/ layout explained | | docs/guide/03-configuration.md | settings.json + auth.json full reference | | docs/guide/04-agents.md | agent.json, AGENT.md, all 4 modes | | docs/guide/05-cli.md | veil CLI commands reference | | docs/guide/06-tools.md | All 24 built-in tools | | docs/guide/07-permissions.md | Permissions system | | docs/guide/08-memory.md | Memory + context compaction | | docs/guide/09-multi-agent.md | Orchestration patterns |

CLI Reference (Quick)

veil start [--port 5050] [--folder ./workspace] [--secret <token>]
veil stop
veil status
veil agents list
veil agents inspect <name>
veil login --key <api-key> [--global]

# Talk to the instance already running in this project:
veil send "<message>" (--session <id> | --agent <name>)   # fire-and-forget
veil sessions [--agent <name>]                            # list sessions
veil state --session <id>                                 # inspect a session
veil suspend --session <id>                               # park a session
veil resume  --session <id>                               # reactivate it

→ Full reference: docs/guide/05-cli.md

Project Layout

VeilCli/
  cli/          ← Veil CLI entry point
  api/          ← Express REST server + routes
  core/         ← agent loader, loop, router, memory, compaction
  engines/      ← provider-specific LLM adapters (claude-cli engine)
  tools/        ← 24 built-in tools
  infrastructure/ ← SQLite database
  utils/        ← settings, paths, context
  schemas/      ← JSON schemas for agent.json and settings.json
  system-prompts/ ← base system prompt layers
  examples/     ← reference agent definitions

License

MIT