Skip to main content

WASP Documentation

WASP is a fully autonomous AI agent platform. It receives natural language instructions via Telegram or its web dashboard, decomposes them into executable plans, runs those plans using a rich skill library, and continuously learns from its experience.

What makes WASP different​

Unlike simple chatbots or prompt-chaining tools, WASP operates as a self-governing agent:

  • Plans autonomously — given any objective, WASP generates a multi-step execution plan via a dual-layer planner with a built-in critic
  • Executes with real skills — web search, full browser control (Chromium), Python execution, shell access, Gmail, file operations, and 30+ more
  • Learns from experience — behavioral corrections, episodic memory, procedural memory, and a skill evolution engine
  • Reasons about time — a temporal world model tracks real-world changes and trends across conversations
  • Runs in the background — 23 scheduled jobs operate continuously without user interaction, including dream consolidation, autonomous goal generation, and background perception

Platform Architecture​

┌─────────────────────────────────────────────────────────┐
│                    Telegram / Dashboard                  │
│              (agent-telegram / agent-nginx)              │
└────────────────────────┬────────────────────────────────┘
                         │ Redis Streams (events:incoming)
┌────────────────────────▼────────────────────────────────┐
│                     agent-core                           │
│  ┌──────────────┐  ┌─────────────┐  ┌───────────────┐  │
│  │ EventHandler │  │  Scheduler  │  │ GoalOrchestra │  │
│  │  (handlers)  │  │  (23 jobs)  │  │   tor + Plan  │  │
│  └──────┬───────┘  └─────────────┘  └───────────────┘  │
│         │                                               │
│  ┌──────▼───────┐  ┌─────────────┐  ┌───────────────┐  │
│  │  ModelManager│  │ SkillExecut │  │  MemoryManager│  │
│  │  (10+ LLMs)  │  │    or       │  │  (8 systems)  │  │
│  └──────────────┘  └─────────────┘  └───────────────┘  │
└─────────────────────────────────────────────────────────┘
           │                              │
    ┌──────▼──────┐               ┌───────▼──────┐
    │ agent-redis │               │agent-postgres│
    │(streams/KV) │               │ (18 tables)  │
    └─────────────┘               └──────────────┘

Key Systems​

SystemDescription
Goal EngineDecomposes objectives into TaskGraphs, executes with plan critic validation
Skill System30+ built-in skills across 5 capability levels, supports custom Python skills
Memory8 persistent memory systems: episodic, semantic, procedural, visual, vector, KG, self-model, temporal
Scheduler23 background jobs covering health, learning, perception, and autonomous goal generation
Multi-AgentSpawn and coordinate multiple sub-agents with independent goal queues
Integrations33 connector types: Slack, Discord, GitHub, Notion, Telegram, Gmail, smart home, and more

Quick Navigation​