> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openpawz.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Features

> The most comprehensive AI agent platform ever built — 25,000+ integrations via MCP bridge, multi-agent, multi-channel, voice, trading, memory, and security.

## Platform features

OpenPawz ships with **more capabilities than any other AI agent platform** — open source or commercial. No other tool combines 25,000+ integrations (via MCP bridge to n8n), multi-agent orchestration, 11 simultaneous chat channels, multi-chain DeFi trading, semantic memory with hybrid retrieval, voice, a visual flow builder, and a three-tier extension marketplace — all running locally on your desktop with zero cloud dependency.

This is the complete feature inventory.

***

## Agents

<Columns cols={2}>
  <Card title="Custom personalities">
    Each agent has a name, bio, system prompt, emoji, and avatar. Three personality axes — **tone** (casual → formal), **initiative** (reactive → proactive), and **detail** (brief → thorough) — let you fine-tune behavior without prompt engineering.
  </Card>

  <Card title="Agent templates">
    Pre-built archetypes — General, Research, Creative, Technical, Custom — so you're productive in seconds. Templates set personality, system prompt, and tool access automatically.
  </Card>

  <Card title="25,000+ integrations">
    400+ native integrations compiled into the binary, plus 25,000+ community integrations via the MCP Bridge to n8n. Agents discover and auto-deploy workflows at runtime, on demand.
  </Card>

  <Card title="Soul files">
    Persistent identity documents for each agent. Soul files store personality notes, custom instructions, and identity data that persist across sessions. Your agent evolves over time.
  </Card>

  <Card title="Per-agent workspaces">
    Every agent gets an isolated filesystem workspace with file listing, browsing, and cleanup. Agents can't accidentally interfere with each other's files.
  </Card>

  <Card title="Agent boundaries">
    Define what each agent should and shouldn't do. Boundary rules constrain behavior without complex prompt engineering — just plain language rules.
  </Card>

  <Card title="Per-agent model override">
    Each agent can use a different AI model, overriding the global default. Run your research agent on Claude, your coder on GPT-4o, and your assistant on a local Ollama model — simultaneously.
  </Card>

  <Card title="Auto-approve mode">
    Trusted agents can skip human-in-the-loop approval prompts entirely. Toggle per agent — full autonomy for agents you trust, strict oversight for new ones.
  </Card>
</Columns>

→ Deep dive: [Agents guide](/guides/agents)

***

## 11 simultaneous channels

**No other AI agent platform connects to this many platforms at once.** One app, one set of agents, eleven live bridges — running simultaneously. A user messages you on Telegram, another on Discord, a third on Slack — the same agent (or different agents) respond instantly on each platform.

| Channel        | Type        | Key capabilities                                                   |
| -------------- | ----------- | ------------------------------------------------------------------ |
| Telegram       | Bot API     | DM policy, user allowlists, pairing approval                       |
| Discord        | Bot         | Mention-response mode, DM policy, user approval                    |
| Slack          | Socket Mode | App + bot tokens, mention-response, DM policy                      |
| Matrix         | Client      | Homeserver auth, room response, DM policy                          |
| IRC            | TLS Client  | Multi-channel join, channel response toggle                        |
| WhatsApp       | Web bridge  | Evolution API, Docker management, QR pairing, group response       |
| Twitch         | Chat        | OAuth bot, multi-channel, mention-require toggle                   |
| Mattermost     | Bot         | Server + token auth, mention-response, DM policy                   |
| Nextcloud Talk | Bot         | Username/password auth, group response toggle                      |
| Nostr          | Relay       | NIP-04 encrypted DMs, Ed25519 signing, multi-relay WebSocket       |
| Webchat        | Built-in    | TLS WebSocket, cookie auth, inline HTML/JS/CSS, session management |

<Columns cols={2}>
  <Card title="Uniform access control">
    Every channel has the same interface: start/stop, config get/set, status, approve/deny/remove users. Consistent behavior across all 11 platforms.
  </Card>

  <Card title="Per-channel agent routing">
    Assign a specific agent to each channel. Your support bot handles Discord, your research agent handles Slack, your personal assistant handles Telegram — all from one app.
  </Card>

  <Card title="Channel routing rules">
    Rule-based routing engine with first-match logic. Route messages to specific agents based on channel, user, keywords, or custom conditions.
  </Card>

  <Card title="Smart message splitting">
    Long responses automatically split at platform-appropriate boundaries. Discord's 2000-char limit, Telegram's 4096-char limit — handled transparently.
  </Card>
</Columns>

→ Deep dive: [Channels overview](/channels/overview)

***

## AI providers

Bring your own model. OpenPawz supports **10 providers** — local and cloud — and you can switch between them per agent, per task, or per conversation.

| Provider   | Type  | Models                                              |
| ---------- | ----- | --------------------------------------------------- |
| Ollama     | Local | Llama, Mistral, Gemma, Phi, Qwen, and hundreds more |
| OpenAI     | Cloud | GPT-4o, o1, o3, GPT-4.1                             |
| Anthropic  | Cloud | Claude 4, Sonnet, Haiku                             |
| Google     | Cloud | Gemini 2.x                                          |
| DeepSeek   | Cloud | DeepSeek V3, R1                                     |
| Grok       | Cloud | Grok 3                                              |
| Mistral    | Cloud | Mistral Large, Codestral                            |
| OpenRouter | Cloud | Multi-model gateway                                 |
| Moonshot   | Cloud | Kimi                                                |
| Custom     | Any   | Any OpenAI-compatible endpoint                      |

<Columns cols={2}>
  <Card title="Model routing">
    Boss model vs worker model assignment. OpenPawz automatically routes simple queries to cheaper models and complex tasks to powerful ones — **saving you money without sacrificing quality**.
  </Card>

  <Card title="SSE streaming">
    All providers stream responses via Server-Sent Events with real-time deltas. You see tokens appear as the model thinks — no waiting for the full response.
  </Card>

  <Card title="Thinking & reasoning blocks">
    Full support for Anthropic thinking blocks and Google thought handling. See the model's reasoning process in real time.
  </Card>

  <Card title="Daily budget enforcement">
    Set a hard USD spending cap per day. When the budget is reached, API calls are blocked. Never get surprised by a bill again. **No other platform has this.**
  </Card>
</Columns>

→ Deep dive: [Providers overview](/providers/overview)

***

## Integrations — 25,000+ via MCP Bridge

**400+ integrations compiled into the Rust binary** — no plugins to install, no marketplace to browse. Configure credentials and assign to agents.

Plus **25,000+ community integrations** via the embedded n8n engine and MCP Bridge. Agents discover, auto-install community packages, and auto-deploy per-service workflows — with zero configuration and low cost (or zero cost with a local Ollama worker).

→ Deep dive: [MCP Bridge guide](/guides/mcp-bridge)

| Category               | Count | Examples                                                                 |
| ---------------------- | ----- | ------------------------------------------------------------------------ |
| Productivity           | 40+   | Notion, Trello, Obsidian, Linear, Jira, Asana, Todoist, Google Workspace |
| Communication          | 30+   | Slack, Discord, Telegram, WhatsApp, Teams, Email (IMAP/SMTP)             |
| Development            | 50+   | GitHub, GitLab, Bitbucket, Docker, Kubernetes, Vercel, Netlify, AWS      |
| Data & Analytics       | 35+   | PostgreSQL, MongoDB, Redis, Elasticsearch, BigQuery, Snowflake           |
| Media & Content        | 25+   | Spotify, YouTube, Whisper, ElevenLabs, Image Gen, DALL-E                 |
| Smart Home & IoT       | 20+   | Philips Hue, Sonos, Home Assistant, MQTT, Zigbee                         |
| Finance & Trading      | 30+   | Coinbase, Solana DEX, Ethereum DEX, Stripe, PayPal, QuickBooks           |
| Cloud & Infrastructure | 40+   | AWS, GCP, Azure, Cloudflare, DigitalOcean, Terraform                     |
| Security & Monitoring  | 25+   | 1Password, Vault, Datadog, PagerDuty, Sentry, Grafana                    |
| AI & ML                | 20+   | Hugging Face, Replicate, Stability AI, Pinecone, Weaviate                |
| CRM & Marketing        | 30+   | Salesforce, HubSpot, Mailchimp, SendGrid, Intercom                       |
| Miscellaneous          | 55+   | Weather, RSS, Web Scraping, PDF, OCR, QR codes, Maps                     |

<Tabs>
  <Tab title="Core tools">
    | Tool               | What it does                                                               |
    | ------------------ | -------------------------------------------------------------------------- |
    | Shell execution    | Run arbitrary commands with risk classification                            |
    | File operations    | Read, write, append, delete, list files in agent workspaces                |
    | Web fetch          | HTTP fetch with configurable domain allowlists/blocklists                  |
    | Browser automation | Headless Chrome — navigate, screenshot, extract, click, fill forms         |
    | Email              | Full IMAP/SMTP: read, send, search, folder management, AI draft generation |
    | GitHub             | Repo operations, issues, PRs, code search                                  |
    | Memory             | Store, search, list, delete semantic memories                              |
    | Tasks              | Create, update, move tasks on the Kanban board                             |
  </Tab>

  <Tab title="Agent tools">
    | Tool                  | What it does                                                                |
    | --------------------- | --------------------------------------------------------------------------- |
    | Inter-agent messaging | Direct messages and broadcasts between agents                               |
    | Agent management      | Agents can create, configure, and manage other agents programmatically      |
    | Agent squads          | Create and manage persistent groups of agents with coordinator/member roles |
    | Soul/persona files    | Read and write persistent personality and identity data                     |
    | Skill output          | Persist structured JSON data for dashboard widgets                          |
    | Skill storage         | Persistent key-value store for extensions — get, set, query, delete         |
  </Tab>

  <Tab title="Trading tools">
    | Tool                | What it does                                                                |
    | ------------------- | --------------------------------------------------------------------------- |
    | Coinbase            | Exchange trading: orders, balances, candle data                             |
    | Solana DEX          | Jupiter aggregator swaps, Pump.fun, SOL/token transfers, portfolio tracking |
    | Ethereum DEX        | Uniswap V2/V3 swaps, ERC-20 ops, HD wallet (BIP-39/44), token discovery     |
    | Position monitoring | Open positions with stop-loss, take-profit, last price tracking             |
    | Price feeds         | Real-time token price data across chains                                    |
  </Tab>

  <Tab title="Voice tools">
    | Tool           | What it does                                                                     |
    | -------------- | -------------------------------------------------------------------------------- |
    | Text-to-speech | Three providers: Google, OpenAI, ElevenLabs. Configurable voice, speed, language |
    | Speech-to-text | Audio transcription via whisper-compatible engines                               |
    | Auto-speak     | Automatically voice all new agent responses. Toggle per session                  |
  </Tab>

  <Tab title="Community tools">
    | Tool             | What it does                                                        |
    | ---------------- | ------------------------------------------------------------------- |
    | Skill search     | Agents search the PawzHub marketplace for new capabilities          |
    | Skill install    | Agents install skills for themselves — at runtime, conversationally |
    | Skill list       | List all installed skills with status and capabilities              |
    | Image generation | Create images via AI with auto-approval                             |
  </Tab>
</Tabs>

***

## Extensibility — three tiers + marketplace

OpenPawz has the most sophisticated extension system of any agent platform. **Three tiers** let you start simple and graduate to full apps — plus a community marketplace.

<Tabs>
  <Tab title="Skills (Tier 1)">
    **Drop a markdown file.** That's it. A `SKILL.md` file injects expert knowledge into an agent's system prompt. No code, no config, no API — just markdown. Hot-reloaded from `~/.paw/skills/` with no restart needed.
  </Tab>

  <Tab title="Integrations (Tier 2)">
    **Custom tools + commands.** A `pawz-skill.toml` manifest adds credentials, binary detection, agent tools, and dashboard widgets. Full Tauri API access.
  </Tab>

  <Tab title="Extensions (Tier 3)">
    **Full sidebar applications.** Build complete sidebar views with persistent key-value storage, custom UI panels, and dashboard widgets. The most powerful tier.
  </Tab>

  <Tab title="MCP">
    **Model Context Protocol.** Connect to any MCP server — stdio or Streamable HTTP transport — for unlimited external tools. Databases, APIs, file systems, and more.
  </Tab>

  <Tab title="PawzHub marketplace">
    **Discover and share.** Browse community-built skills, integrations, and extensions. Search by keyword, filter by tier. Visual badge system: Blue (Skill), Purple (Integration), Gold (Extension), plus Verified, Official, and Popular tags.
  </Tab>
</Tabs>

<Columns cols={2}>
  <Card title="Agent-installable skills">
    **No other platform has this.** Agents can conversationally search PawzHub, discover new capabilities, and install skills for themselves — at runtime. Your AI agent literally improves itself.
  </Card>

  <Card title="Skill Wizard">
    AI-assisted TOML manifest generation. Paste an API's documentation and the wizard generates a complete integration manifest automatically.
  </Card>

  <Card title="TOML hot reload">
    Drop a new `.toml` file into `~/.paw/skills/` and it's instantly available. No restart, no rebuild, no deployment. The filesystem is your package manager.
  </Card>

  <Card title="Per-agent skill scoping">
    Skills, integrations, and extensions can be enabled for specific agents only. Your research agent gets web tools, your support agent gets email tools — no overlap.
  </Card>
</Columns>

→ Deep dive: [Skills](/guides/skills) · [Integrations](/guides/integrations) · [Extensions](/guides/extensions)

***

## Multi-agent orchestration

<Columns cols={2}>
  <Card title="Boss/worker delegation">
    A boss agent plans a project and delegates tasks to specialist workers. Workers run in parallel, report results, and the boss synthesizes the output. Full lifecycle: planning → running → paused → completed → failed.
  </Card>

  <Card title="Agent squads">
    **Unique to OpenPawz.** Persistent groups of agents with coordinator and member roles. Create a "Research Squad" or "Content Team" and reuse them across projects. Squads coordinate automatically.
  </Card>

  <Card title="Agent specialties">
    Assign workers a specialty — coder, researcher, designer, communicator, security, general. Each worker can have its own model and system prompt within a project.
  </Card>

  <Card title="Inter-agent messaging">
    Agents send direct messages to specific agents or broadcast to all. Full delegation, progress, result, and error message streams between boss and workers.
  </Card>
</Columns>

<Columns cols={2}>
  <Card title="Task management">
    Full Kanban board with columns: inbox, assigned, in progress, review, blocked, done. Tasks have priorities (low → urgent), multi-agent assignment with lead/collaborator roles, and per-task model overrides.
  </Card>

  <Card title="Automations">
    Cron scheduling with 60-second heartbeat, event-driven triggers, persistent execution mode, and a full cron run log with audit trail. Schedule agents to run research at 2 AM, post updates at 9 AM, clean up at midnight.
  </Card>
</Columns>

→ Deep dive: [Orchestrator](/guides/orchestrator) · [Automations](/guides/automations)

***

## Memory — the most advanced retrieval system in any agent platform

Most AI tools forget everything between conversations. OpenPawz has the most sophisticated memory system available — **four retrieval strategies combined**.

<Columns cols={2}>
  <Card title="Hybrid retrieval">
    **No other platform does this.** BM25 full-text search + vector similarity (cosine) combined with weighted merging. You get the precision of keyword search and the flexibility of semantic search — together.
  </Card>

  <Card title="MMR re-ranking">
    Maximal Marginal Relevance with Jaccard-based diversity ensures recalled memories are both relevant AND diverse. No more getting five copies of the same memory.
  </Card>

  <Card title="Temporal decay">
    Exponential decay with a 30-day half-life. Recent memories rank higher than old ones. Your agent prioritizes what's current without losing long-term knowledge.
  </Card>

  <Card title="Auto-capture & auto-recall">
    Key facts are automatically extracted from every conversation and stored with vector embeddings. When context is relevant, memories are injected before the agent responds — zero manual effort.
  </Card>
</Columns>

<Columns cols={2}>
  <Card title="Memory Palace">
    A dedicated interface to browse, search, edit, and delete memories. Filter by agent, topic, date, category, or relevance score. Full transparency into what your AI knows.
  </Card>

  <Card title="Importance scoring">
    Each memory receives an importance score (0–1). Critical facts rank higher than casual observations. The system learns what matters.
  </Card>

  <Card title="Memory backfill">
    Retroactively generate vector embeddings for existing memories. Upgrade your memory system without starting over.
  </Card>

  <Card title="Shared & isolated namespaces">
    All agents share memory by default — knowledge captured by one is available to all. Isolate per agent or per workspace when you need boundaries.
  </Card>
</Columns>

→ Deep dive: [Memory guide](/guides/memory)

***

## Session management & token savings

<Columns cols={2}>
  <Card title="Automatic session compaction">
    When conversations approach the context limit, OpenPawz summarizes older messages, preserves key facts in memory, archives the full session, and continues seamlessly. Agents run **indefinitely long conversations** — and you pay for 40–60% fewer tokens.
  </Card>

  <Card title="Thinking level control">
    **Unique to OpenPawz.** Adjust reasoning depth per session — none, low, medium, high. Need a quick answer? Use low. Complex analysis? Crank it up. You control the compute.
  </Card>

  <Card title="Configurable context windows">
    Set the context window size in tokens (default 32,000). Larger windows for complex tasks, smaller ones for cost savings. Per-session control.
  </Card>

  <Card title="Max concurrent runs">
    Limit simultaneous agent runs across chat, cron, and tasks. Chat always gets priority. Prevent runaway costs from parallel automations.
  </Card>
</Columns>

→ Deep dive: [Sessions guide](/guides/sessions)

***

## DeFi trading — multi-chain, built-in

**No other AI agent platform has built-in, multi-chain cryptocurrency trading.** OpenPawz agents can trade on Coinbase, Solana (via Jupiter/Pump.fun), and Ethereum (via Uniswap) — autonomously, with configurable safety guardrails.

<Columns cols={2}>
  <Card title="Coinbase exchange">
    Full exchange trading via Coinbase API: limit/market orders, account balances, candle data, trade history.
  </Card>

  <Card title="Solana DEX">
    Jupiter aggregator for best-price swaps, Pump.fun integration for memecoins, Ed25519 wallet management, SOL/SPL token transfers, portfolio tracking.
  </Card>

  <Card title="Ethereum DEX">
    Uniswap V2/V3 swaps, full ABI/RLP encoding, HD wallet (BIP-39/44), ERC-20 operations, token discovery, liquidity analysis.
  </Card>

  <Card title="Position monitoring">
    Track open positions with stop-loss and take-profit targets. Real-time price feeds across chains. Aggregate portfolio view.
  </Card>
</Columns>

<Columns cols={2}>
  <Card title="Trading policy engine">
    **Unique to OpenPawz.** Configurable auto-approve rules with max trade size (USD), daily loss limits, allowed pairs whitelist, and transfer caps. Agents trade autonomously within guardrails you set.
  </Card>

  <Card title="Trade audit trail">
    Every trade logged: type, side, amount, USD value, reason, agent, session, timestamp. Full accountability for autonomous trading decisions.
  </Card>
</Columns>

→ Deep dive: [Trading guide](/guides/trading)

***

## Voice — text-to-speech & speech-to-text

<Columns cols={2}>
  <Card title="Three TTS providers">
    Choose between Google TTS, OpenAI TTS, or ElevenLabs. Configurable voice selection, speed, and language per agent.
  </Card>

  <Card title="Speech-to-text">
    Audio transcription via Whisper-compatible engines. Speak to your agents and they understand.
  </Card>

  <Card title="ElevenLabs integration">
    Advanced voice controls: model selection, stability sliders, similarity boost. Professional-grade voice output.
  </Card>

  <Card title="Auto-speak">
    Toggle automatic voicing of all new agent responses. Your agents become voice assistants — read responses aloud as they arrive.
  </Card>
</Columns>

→ Deep dive: [Voice guide](/guides/voice)

***

## Security — zero-trust, local-first

OpenPawz was designed from the ground up with a **zero-trust, local-first security model**. This isn't an afterthought bolted on — it's in the architecture.

<Columns cols={2}>
  <Card title="100% local — zero cloud">
    All data stays on your hardware. No cloud sync, no telemetry, no analytics, no phone-home. The only outbound traffic is to AI providers you explicitly configure.
  </Card>

  <Card title="OS keychain credentials">
    API keys stored in macOS Keychain, Windows Credential Manager, or Linux Secret Service. Never in plain text. Never in a config file.
  </Card>

  <Card title="AES-256-GCM encryption">
    Database fields encrypted with AES-256-GCM using 12-byte random nonces. Auto-migration from legacy encryption. Your data is encrypted at rest.
  </Card>

  <Card title="Command risk classification">
    Every tool and shell command rated 1–5 for risk. 30+ danger pattern detections: privilege escalation, destructive deletion, remote code execution, network exfiltration.
  </Card>

  <Card title="Human-in-the-loop">
    Modal-based approval for all side-effect tools. Color-coded risk levels. Nothing dangerous happens without your explicit confirmation.
  </Card>

  <Card title="Timed session override">
    **Unique to OpenPawz.** "Allow All" mode for trusted sessions (30m/1h/2h) with auto-expire. Privilege escalation is still blocked — even in override mode.
  </Card>
</Columns>

<Columns cols={2}>
  <Card title="Container sandbox">
    Run agent shell commands in Docker containers — cap\_drop ALL, memory/CPU limits, configurable network isolation. Agents can't touch your host system.
  </Card>

  <Card title="Per-agent policies">
    Granular control over which tools, channels, and risk levels each agent can access.
  </Card>

  <Card title="Prompt injection defense">
    Dual implementation (TypeScript + Rust), 30+ detection patterns, 4 severity levels. Incoming messages are analyzed before they reach agents.
  </Card>

  <Card title="Filesystem sandboxing">
    Tauri scope enforcement with 20+ sensitive path blocks — `~/.ssh`, `~/.aws`, `~/.gnupg`, and more. Optional global read-only mode blocks all agent writes.
  </Card>

  <Card title="Outbound domain control">
    Configurable domain allowlists and blocklists with wildcard subdomain matching. Test URL button to verify rules. Outbound requests inspected for exfiltration patterns.
  </Card>

  <Card title="Credential audit trail">
    **Unique to OpenPawz.** Every credential access logged: action, tool, allowed/denied, timestamp. Full security audit dashboard with JSON/CSV export.
  </Card>
</Columns>

<Columns cols={2}>
  <Card title="Skill vetting pipeline">
    **Unique to OpenPawz.** Community skills go through a safety modal, known-safe list check, npm registry risk intelligence scan, and post-install sandbox verification.
  </Card>

  <Card title="CSP enforcement">
    Content Security Policy: `default-src 'self'`, `script-src 'self'`, `object-src 'none'`, `frame-ancestors 'none'`. XSS and injection prevention at the platform level.
  </Card>
</Columns>

<Columns cols={2}>
  <Card title="TLS certificate pinning">
    **Unique to OpenPawz.** Custom `rustls` config pinned to Mozilla root CAs only — OS trust store explicitly excluded. Even a compromised CA on the user's machine cannot MITM provider traffic.
  </Card>

  <Card title="Outbound request signing">
    Every AI provider request SHA-256 signed before transmission. Hash of `provider ‖ model ‖ timestamp ‖ body` logged to a 500-entry audit ring buffer for tamper detection and compliance.
  </Card>

  <Card title="Memory encryption (RAM zeroing)">
    API keys wrapped in `Zeroizing<String>` — memory automatically overwritten with zeros on drop via `write_volatile`. Prevents memory dump, swap file, and use-after-free key extraction.
  </Card>

  <Card title="Shared pinned HTTP client">
    Singleton `reqwest::Client` with pinned TLS config shared across all providers. Connection pooling, 10s connect timeout, 120s request timeout. No per-request client creation overhead.
  </Card>
</Columns>

→ Deep dive: [Security reference](/reference/security)

***

## Flows — visual workflow builder

**Unique to OpenPawz.** A drag-and-drop visual workflow engine for building multi-step AI pipelines. Wire together integrations — triggers, agents, tools, conditions, code, data transforms, and outputs — on an SVG canvas with real-time execution feedback.

<Columns cols={2}>
  <Card title="10 integration types">
    Trigger, Agent, Tool, Condition, Data, Code, Output, Error, Group, and **Event Horizon** (tesseract synchronization barrier). Each has its own icon, color, and configuration panel.
  </Card>

  <Card title="Conductor Protocol">
    **Unique to OpenPawz.** Automatic graph optimization that detects parallelism, collapses sequences, and compiles execution strategies — 5 primitives including Tesseract for 4D cell-based orchestration.
  </Card>

  <Card title="Tesseract flows">
    **Unique to OpenPawz.** Partition complex graphs into independent cells that execute in parallel, synchronized at event horizons. Per-cell memory isolation, per-cell timeouts, and graceful degradation.
  </Card>

  <Card title="Flow memory integration">
    Agent nodes automatically receive relevant long-term memories from Engram. In tesseract flows, each cell gets its own scoped memory context — no shared-state races.
  </Card>

  <Card title="Text-to-flow">
    Type a natural-language description — `webhook → agent → send email` — and the parser builds the flow automatically with correct integration types and edges.
  </Card>

  <Card title="Debug mode">
    Step through flows one integration at a time. Set breakpoints, inspect intermediate data on edges, and watch the execution cursor move across the canvas.
  </Card>

  <Card title="Code integrations">
    Run sandboxed JavaScript inline. Access `input` from the previous step and `context` for flow metadata. Return values flow downstream.
  </Card>

  <Card title="4 edge types">
    Forward, Reverse, Bidirectional, and Error edges control data flow direction. Wire complex handshakes and fallback paths on the canvas.
  </Card>

  <Card title="Templates">
    30+ pre-built flow patterns across 10 categories — AI, Communication, DevOps, Productivity, Data, Research, Social, Finance, Support, and Custom.
  </Card>

  <Card title="Schedule & cron">
    Attach cron expressions to any flow. The scheduler fires every 30 seconds. Hero stats show active schedule count.
  </Card>

  <Card title="Folder organization">
    Organize flows into folders with collapsible sidebar groups. Drag-and-drop between folders.
  </Card>

  <Card title="Chat reporter">
    Every execution posts a live flow report into chat — progress bar, per-step status, timing, and a final summary.
  </Card>
</Columns>

→ Deep dive: [Flows guide](/guides/flows)

***

## Foundry — skill creation workshop

The Foundry is a dedicated workspace for creating and testing skills, integrations, and extensions. AI-assisted manifest generation, live preview, and one-click publishing to PawzHub.

→ Deep dive: [Foundry guide](/guides/foundry)

***

## Today View — your AI dashboard

A daily activity dashboard that shows everything your agents have been doing. Activity feed, quick actions, inbox, and status across all agents, channels, and automations — at a glance.

→ Deep dive: [Dashboard guide](/guides/dashboard)

***

## Email — full IMAP/SMTP client

Not a toy integration — a complete email client. IMAP/SMTP via himalaya bridge: read, send, search, folder management, AI-powered draft generation. Multiple accounts, folder operations, and a dedicated Mail view in the app.

→ Deep dive: [Email guide](/guides/email)

***

## Remote access

<Columns cols={2}>
  <Card title="Tailscale integration">
    **Unique to OpenPawz.** Expose your agents remotely via Tailscale mesh VPN. Serve and Funnel support for secure remote access — no port forwarding, no cloud relay. Connect from anywhere.
  </Card>

  <Card title="Webhook server">
    Built-in HTTP webhook endpoint with auth token, rate limiting, and configurable agent routing. Trigger agents from GitHub Actions, Zapier, IFTTT, or any HTTP client.
  </Card>
</Columns>

→ Deep dive: [Tailscale guide](/guides/tailscale)

***

## Developer experience

<Columns cols={2}>
  <Card title="20 slash commands">
    Built-in slash commands with real-time autocomplete. Quick access to common operations without leaving the chat.
  </Card>

  <Card title="Modular workspace">
    Toggle grid for showing/hiding UI views. Community extensions add to this grid. Customize the interface for your workflow.
  </Card>

  <Card title="14 settings tabs">
    Agent defaults, providers, sessions, skills, MCP, browser, engine, environment, logs, voice, webhook, Tailscale, and more. Everything is configurable.
  </Card>

  <Card title="Persistent structured logging">
    Daily log rotation with 7-day pruning and an in-app log viewer with filtering. Debug anything without digging through files.
  </Card>
</Columns>

***

## Architecture & quality

<Columns cols={2}>
  <Card title="Native Tauri v2">
    Rust backend + TypeScript frontend. Not Electron — fast, lean, native. 158 IPC commands covering every engine operation.
  </Card>

  <Card title="Zero-framework frontend">
    Vanilla TypeScript with atomic design (atoms → molecules → organisms). No React, no Vue, no Angular. Minimal bundle, maximum performance.
  </Card>

  <Card title="2,816 automated tests">
    650 Rust + 2,166 TypeScript tests covering all critical paths including the Conductor Protocol, tesseract flows, and memory integration. 3-job CI pipeline (Rust + TypeScript + Security Audit) on every push.
  </Card>

  <Card title="Zero known CVEs">
    `cargo audit` + `npm audit` enforced in CI. Zero Clippy warnings. Dependabot for automated dependency updates.
  </Card>

  <Card title="21 SQLite tables">
    Full relational schema for agents, sessions, memories, tasks, trades, skills, channels, and more. All local, all fast.
  </Card>

  <Card title="Retry with circuit breakers">
    Exponential backoff (1s → 30s, 3 retries), `Retry-After` header support, 5-failure circuit breaker with 60-second cooldown. Resilient by default.
  </Card>
</Columns>

→ Deep dive: [Architecture reference](/reference/architecture) · [Quality reference](/reference/quality)

***

## What exists like this? Nothing.

| Capability                    | **OpenPawz**                                                         | **OpenClaw** | **AutoGPT**  | **CrewAI**      | **LangChain**    |
| ----------------------------- | -------------------------------------------------------------------- | ------------ | ------------ | --------------- | ---------------- |
| **Desktop native app**        | Tauri/Rust                                                           | Electron     | No — CLI/web | No — Python lib | No — Python lib  |
| **Chat channels**             | 11 simultaneous                                                      | 1–2          | 0            | 0               | 0                |
| **Multi-agent orchestration** | Boss/worker + squads                                                 | Basic        | Single agent | Yes             | Yes (framework)  |
| **Semantic memory**           | Hybrid BM25+vector+MMR+decay                                         | Basic        | Basic        | None built-in   | Framework only   |
| **Built-in integrations**     | 25,000+ (400 native + MCP bridge)                                    | \~20         | \~15         | Code-defined    | Framework only   |
| **DeFi trading**              | 3 chains                                                             | None         | None         | None            | None             |
| **Voice (TTS/STT)**           | 3 providers                                                          | None         | None         | None            | None             |
| **Extension marketplace**     | 3 tiers + PawzHub                                                    | None         | Plugin store | None            | LangSmith        |
| **Self-installing skills**    | Agents install their own                                             | No           | No           | No              | No               |
| **Visual flow builder**       | Built-in (10 types, Conductor Protocol, Tesseract, debug, templates) | No           | No           | No              | LangGraph Studio |
| **Session compaction**        | Automatic, 40–60% savings                                            | No           | No           | No              | No               |
| **Daily budget caps**         | Built-in USD cap                                                     | No           | No           | No              | No               |
| **Security audit trail**      | Full + export                                                        | Basic        | None         | None            | None             |
| **TLS cert pinning**          | ✅ Mozilla-only                                                       | ❌ OS default | ❌            | ❌               | ❌                |
| **Request signing**           | ✅ SHA-256 audit                                                      | ❌            | ❌            | ❌               | ❌                |
| **Memory zeroing**            | ✅ Zeroize on drop                                                    | ❌            | ❌            | ❌               | ❌                |
| **Webhooks + Tailscale**      | Built-in                                                             | None         | None         | None            | None             |
| **Credential security**       | OS keychain + AES-256                                                | Config files | Config files | Env vars        | Env vars         |
| **Open source**               | MIT                                                                  | MIT          | MIT          | MIT             | MIT              |

**OpenPawz is the first AI agent operating system** that combines 25,000+ integrations (via MCP bridge), multi-agent orchestration, 11 channels, DeFi trading, memory, voice, a visual flow builder, and a three-tier marketplace in a single, native, open-source desktop application. Nothing else comes close.