Roadmap
Current Status
WASP is in active production deployment. The following systems are complete and operational:
Completed Systems (19 total)
- Event-driven architecture (Redis Streams)
- Goal Engine with TaskGraph execution
- Dual-layer planning (PlanGenerator + PlanCritic)
- 30+ built-in skills
- Custom Python skill creation
- Skill Evolution (automatic synthesis)
- 23 scheduler background jobs
- 8 memory systems (episodic, semantic, procedural, visual, vector, KG, self-model, temporal)
- Knowledge Graph with Redis cache
- Temporal World Model
- Multi-agent orchestration
- Dream Mode (memory consolidation)
- Autonomous Goal Generator
- Background Perception (crypto monitoring)
- Behavioral Learning Loop
- Epistemic State tracking
- Self-Integrity Monitor
- Cognitive Pressure Index
- 33 integration connectors
- Dashboard with real-time streaming
- Telegram + Dashboard interfaces
- CSRF protection, audit logging, secret redaction
- Self-Repair (SelfHealer)
- Self-Improvement (code patching)
- Sovereign Mode
Planned Features
Near-Term
Vector Memory Enhancement
- Enable by default (currently requires manual Ollama setup)
- Automatic embedding model pull on first enable
- Cross-session semantic memory search
Voice Interface
- Speech-to-text via Telegram voice messages
- Text-to-speech responses
- Wake word detection for local deployment
Structured Output Validation
- JSON schema validation for skill outputs
- Retry with correction when schema mismatch
- Type-safe skill parameter validation
Dashboard Improvements
- Real-time goal execution visualization (node graph)
- Memory timeline view
- Agent performance analytics
Medium-Term
MCP (Model Context Protocol) Full Support
- Connect to any MCP server as a skill source
- MCP server hosting (expose WASP skills as MCP)
- Dynamic tool discovery from MCP endpoints
Multi-Modal Memory
- Store and retrieve audio, video, and document content
- Cross-modal search (text → finds related images)
- Video analysis with frame extraction
Workflow Builder
- Visual workflow editor in the dashboard
- Trigger-based automation (webhook → goal)
- Scheduled workflow templates
Enhanced Security
- Skill sandboxing via container isolation (separate process per skill)
- Fine-grained permission model per user
- Hardware token support for dashboard auth
Long-Term
Meta-Agent Architecture (v2)
- Fully autonomous agent team coordination
- Hierarchical goal decomposition
- Cross-agent memory sharing with privacy controls
- Agent specialization and routing
Federated Deployment
- Multiple WASP instances coordinating
- Distributed goal execution across nodes
- Shared knowledge graph federation
Plugin Marketplace
- Community skill packages
- One-click skill installation via ClawHub
- Skill version management and updates
Learning System v2
- Reinforcement learning from user feedback signals
- Automatic hyperparameter tuning for LLM calls
- Cross-session behavioral pattern mining
Contributing
WASP is under active development. The codebase is structured for extensibility:
- New skills: Add to
src/skills/builtin/or viaskill_manager - New scheduler jobs: Add class to
src/scheduler/and register inmain.py - New connectors: Add to
src/integrations/connectors/and register inmain.py - New memory types: Add module to
src/memory/and inject intobuild_context()
See Extending WASP for implementation guides.
Version History
| Version | Key Feature |
|---|---|
| Phase 1-6 | Core agent, skills, memory, scheduler |
| Phase 7 | Health monitor, self-repair, introspector |
| Phase 8 | Security hardening, dashboard, CSRF |
| Phase 9 | Agent freedom, shell/python/browser skills |
| Phase 10-16 | Cognitive systems (KG, temporal, epistemic, dream) |
| Phase 17 | Multi-agent orchestration |
| Phase 18 | QA/SRE audit, 208 tests |
| Post-18 | Skill evolution, world model, behavioral learning, CPI, integrity monitor |
| Current | Sovereign mode, autonomous goals, self-improvement |