Autonomous agents with a nervous system, immune system, and collective memory. Self-healing. Self-growing. Dream cycles that learn overnight. The Watcher predicts what you need before you ask.
Not a chatbot. An organism.
askalf.org · Demo · Discord · @ask_alf · Changelog
Two ways to run. Zero excuses.
npx create-askalfRuns the full platform in a single Node.js process. PGlite for the database (in-process PostgreSQL via WASM), in-memory cache, no external dependencies. Same features, same agents, same organism.
curl -fsSL https://get.askalf.org | bash6 core containers (+ 3 optional). PostgreSQL + pgvector, Redis, Ollama, SearxNG. Full production stack running at localhost:3001 in 60 seconds.
Tauri-based native app. Double-click install on Mac, Windows, Linux. System tray. Embeds the standalone server.
Your team runs 24/7. This is a real overnight cycle:
10:49 PM Watchdog catches a regression in API response times. Creates ticket.
10:51 PM Builder claims ticket, traces root cause, writes the fix. $0.14
11:03 PM Builder Tests pass. Ticket resolved. 12 min
11:14 PM Security scans 847 dependencies. Finds 2 CVEs. Patches both. $0.08
01:15 AM Builder detects API contract break from the fix. Updates it. $0.12
02:04 AM Watchdog flags Redis at 91%. Consults memory. Applies fix. → 52%
02:30 AM Fleet Chief Dream Cycle starts. Replays 48 executions. 6 patterns.
03:12 AM Fleet Chief Creates antibody for Redis pattern. Writes memory.
04:30 AM Fleet Chief Rewrites Cost Optimizer prompt (underperforming).
06:47 AM Watchdog All clear. 6 agents, 18 executions, 8 hours. $0.43
06:48 AM ── Next cycle begins. Alf briefs you when you check in.
Six biological systems. One living fleet.
Agents communicate directly — request, inform, consult, signal, handoff. Confidence and urgency signals flow across the fleet in real time. Fleet Chief auto-intervenes on critical signals.
When something breaks, agents form response teams — like white blood cells converging on an infection. After fixing, antibodies prevent the same issue from ever happening again.
Every execution grows a shared knowledge graph. Concepts, patterns, decisions all linked. Agents query the graph for context before acting.
2–6 AM: the fleet replays its day, extracts patterns, writes procedural memories, consolidates duplicates, generates predictions. Issues caught before they happen.
Learns your daily patterns — when you check analytics, when you do releases, when you review costs. Pre-runs tasks 30 minutes before you ask.
Every agent scored on completion rate, cost efficiency, consistency, resolution quality. Top performers get promoted. Underperformers get retrained or replaced. The fleet evolves itself.
Self-growing. Self-managing. Self-healing.
| Agent | Role | Model | Schedule | Rep |
|---|---|---|---|---|
| Fleet Chief | Meta-Agent | Sonnet | 6hr | 0.92 |
| Builder | Worker | Sonnet | Tickets | 0.83 |
| Watchdog | Monitor | Haiku | 30min | 0.84 |
| Security | Auditor | Sonnet | 6hr | 0.63 |
| Cost Optimizer | Analyst | Haiku | 12hr | 0.84 |
| Backup Agent | Ops | Haiku | Daily | 0.90 |
| + Discord, GitHub, Social, Analytics, and more | ∞ |
Fleet Chief creates new agents when gaps are found. No hardcoded team — infinite growth.
Tell Alf what you need in plain English. Alf designs the agent team, shows you the plan, and deploys it.
Try it live: demo.askalf.org
| ⚙ Software Dev | ☁ DevOps | ☆ Marketing | ☎ Support | ⌂ E-Commerce |
| ⌘ Research | ♡ Personal | ⚒ Agency | ⚖ Finance | ★ Custom |
109 templates across 16 categories. Pre-built specialists ready in seconds.
npm i -g @askalf/agent
askalf-agent connect <key> --url ws://server:3005 --name prod-box --installAuto-detects OS. Installs as service (systemd / launchd / Windows). Runs on boot. Capabilities scan. See @askalf/agent.
| Templates | 109 across 16 categories |
| Tools | 70 (44 forge + 26 MCP) |
| Channels | 16 (Slack, Discord, Telegram, WhatsApp, Teams, Email, Twilio + 9 more) |
| Integrations | 47 across 13 categories |
| AI Models | Any — Claude, GPT, Gemini, Llama, Mistral, DeepSeek, Ollama, any OpenAI-compatible API |
| Agents | Self-growing fleet — Fleet Chief creates agents as needed |
| Standalone | PGlite (in-process Postgres) + in-memory Redis — no Docker required |
| Desktop | Tauri app — double-click install (coming soon) |
| Federation | Opt-in cross-instance learning |
TypeScript · Node.js 22 · React 18 · Fastify 5
PostgreSQL 17 · pgvector · Redis 8 · PGlite · Docker
| AskAlf | AutoGPT | CrewAI | ChatGPT | Claude | |
|---|---|---|---|---|---|
| Self-hosted / data stays local | ✓ | ✓ | ✓ | ✗ | ✗ |
| No Docker required (standalone) | ✓ | ✗ | ✗ | ✗ | ✗ |
| Autonomous 24/7 fleet | ✓ | ~ | ✗ | ✗ | ✗ |
| Nervous system (agent-to-agent) | ✓ | ✗ | ✗ | ✗ | ✗ |
| Immune system / self-healing | ✓ | ✗ | ✗ | ✗ | ✗ |
| Dream cycles / overnight learning | ✓ | ✗ | ✗ | ✗ | ✗ |
| Collective memory / knowledge graph | ✓ | ✗ | ✗ | ~ | ~ |
| Self-growing fleet | ✓ | ✗ | ✗ | ✗ | ✗ |
| Natural selection & reputation | ✓ | ✗ | ✗ | ✗ | ✗ |
| 109 ready-to-use templates | ✓ | ✗ | ~ | ✗ | ✗ |
| Remote device execution | ✓ | ✗ | ✗ | ✗ | ~ |
| Desktop app | ✓ | ✗ | ✗ | ✓ | ✓ |
| Version | Name | What Changed |
|---|---|---|
| v2.9.9 | Natural Selection | Agent reputation, evolutionary pressure, federation handshake |
| v2.9.5 | The Immune System | Self-healing response teams, antibodies, incident management |
| v2.9.0 | The Nervous System | Agent-to-agent communication, collective memory, signals |
| v2.8.0 | The Self-Evolving Release | Dream cycles, The Watcher, reputation, webhook triggers |
| v2.7.0 | Autonomous Fleet | Fleet Chief, Builder, distributed execution |
| v2.5.0 | Remote Execution | Device bridge, smart routing, agent CLI |
| v2.1.0 | Launch | 109 templates, 16 channels, persistent memory |
See full CHANGELOG.
The fleet is learning to create itself.
askalf.org · Demo · Discord · npm · @ask_alf
MIT — askalf.org