Self-hosted AI agent engine for developers.
35 providers · 72 tools · 22 channels · runs on anything.

Docs · Report Bug · Discord

Chat with Gemma 4 locally. Zero cost. Runs on your Mac.

• Why profClaw
• Features
• Quick Start
• Interactive TUI
• Slash Commands
• Headless Mode
• Deployment Modes
• Where It Runs
• Configuration
• AI Providers
• Chat Channels
• Integrations
• Architecture
• Development
• License

Most AI coding tools are cloud-only (Cursor, Devin) or single-purpose CLIs (Aider, SWE-Agent). profClaw runs on your machine, talks to 35 providers (or none, Ollama works offline), and does more than chat.

• Local-first. Your data stays on your hardware.
• 35 AI providers, including Ollama for fully offline usage.
• Interactive TUI with streaming markdown, syntax highlighting, and a model switcher.
• Routes tasks to the right agent based on capability scoring.
• Real task queue with retry, backoff, and dead letter handling (BullMQ + Redis).
• 22 chat channels: Slack, Discord, Telegram, WhatsApp, Teams, and more.
• Per-token cost tracking with budget alerts.
• 72 built-in tools: file ops, git, browser automation, cron, web search, voice.
• Pico mode runs on a Raspberry Pi Zero 2W in ~140MB RAM.

npm install -g profclaw
profclaw init
profclaw chat --tui

# Verify
curl http://localhost:3000/health

profclaw init scans your project, detects your stack, and writes a PROFCLAW.md context file. It picks up any AI provider keys already in your environment.

profclaw chat --tui opens the terminal UI with streaming responses, code highlighting, slash commands, and a model selector.

npx profclaw onboard

Walks you through provider setup, config, and server start. Takes about 5 minutes.

docker run -d \
  -p 3000:3000 \
  -e ANTHROPIC_API_KEY=sk-ant-xxx \
  -e PROFCLAW_MODE=mini \
  ghcr.io/profclaw/profclaw:latest

git clone https://github.com/profclaw/profclaw.git
cd profclaw
cp .env.example .env
docker compose up -d

Want free local AI? Add Ollama:

docker compose --profile ai up -d

curl -fsSL https://raw.githubusercontent.com/profclaw/profclaw/main/install.sh | bash

profClaw has a full terminal UI. No browser needed.

profclaw chat --tui
# or
profclaw tui

What you get:

• Streaming markdown rendered as the model responds
• Syntax-highlighted code blocks (100+ languages)
• Slash command picker: type / to browse skills
• Model selector: switch providers mid-conversation with Ctrl+M
• Tool execution panel showing every call, argument, and result
• Session history and full keyboard navigation

┌─ profClaw v2.x.x ─────────────────────────────────────────────┐
│  [Chat]                               [Tools]                  │
│                                                                 │
│  You: Review src/auth.ts for security issues                    │
│                                                                 │
│  Agent: I'll analyze auth.ts for security issues.     read_file │
│                                                       ───────── │
│  ## Security Analysis                                 auth.ts   │
│                                                                 │
│  **Critical**: JWT secret read from env without      analyze   │
│  fallback guard on line 42. If `JWT_SECRET` is       ──────── │
│  undefined the app will sign tokens with `undefined`. auth.ts  │
│  ...                                                            │
└─────────────────────────────── [claude-sonnet-4-6] [pro] ──────┘

Type / in any chat to run a skill. Skills are plain Markdown files, easy to create your own.

See Skills docs for all 50 built-in skills and how to create your own with a plain Markdown file.

Run agents from scripts, CI pipelines, or other services:

# One-shot message
profclaw chat "Summarize the last 10 git commits"

# JSON output for scripting
profclaw chat "List open TODOs in src/" --output json

# Run a skill headlessly
profclaw skill run commit --message "feat: add auth"

# Agent task with file context
profclaw agent run "Review src/ for security issues" --files src/

# Verify your setup
profclaw doctor

REST API:

curl -X POST http://localhost:3000/api/chat/message \
  -H "Content-Type: application/json" \
  -d '{"message": "List open GitHub issues", "provider": "anthropic"}'

Same binary, different scale. Set PROFCLAW_MODE and go:

Set via PROFCLAW_MODE=pico|mini|pro environment variable.

profClaw requires Node.js 22+. For bare-metal embedded devices (ESP32, Arduino), see MimiClaw (C) or PicoClaw (Go).

The setup wizard (profclaw onboard) handles everything interactively. Or set environment variables:

# AI Provider (pick one)
ANTHROPIC_API_KEY=sk-ant-xxx
OPENAI_API_KEY=sk-xxx
OLLAMA_BASE_URL=http://localhost:11434

# Deployment
PROFCLAW_MODE=mini
PORT=3000

# Optional
REDIS_URL=redis://localhost:6379   # Required for pro mode

Run profclaw doctor to verify your configuration at any time.

See .env.example for all 130+ options.

35 providers with 90+ model aliases:

src/
  adapters/       AI agent adapters (tool calling, streaming)
  chat/           Chat engine + execution pipeline
    providers/    Slack, Discord, Telegram, WhatsApp, WebChat, ...
    execution/    Tool executor, sandbox, agentic loop
  core/           Deployment modes, feature flags
  integrations/   GitHub, Jira, Linear webhooks
  queue/          BullMQ (pro) + in-memory (pico/mini) task queue
  providers/      35 AI SDK providers
  skills/         Skill loader and registry
  mcp/            MCP server (stdio + SSE)
  tui/            Interactive terminal UI (ink + blessed)
  types/          Shared TypeScript types

ui/src/           React 19 + Vite dashboard (mini/pro only)
skills/           Built-in skill definitions (Markdown)

Design decisions:

• Same binary scales from pico to pro. Features are gated at runtime.
• Adding an AI provider is one file implementing ModelAdapter.
• Skills are plain .md files. No code needed.
• BullMQ for production queues, in-memory fallback for pico/mini.

See Architecture docs for a deep dive.

git clone https://github.com/profclaw/profclaw.git
cd profclaw
pnpm install
cp .env.example .env
pnpm dev

See CONTRIBUTING.md for full guidelines.

See SECURITY.md for our security policy and how to report vulnerabilities.

• Quickstart guide
• Full docs
• Report a bug
• Discord

AGPL-3.0