Darwin 0.1 — Evolution Infrastructure
The first generation establishes evolution itself. Not a model that evolves — an infrastructure that enables any Mind to evolve.
Evolution Infrastructure
✓ CompleteCandidate generation, sandboxing, benchmarking, reviews, promotion, rollback
Mind Runtime
✓ CompleteIntegrated system with task execution, memory, skills, tools, routing
Cognitive Compiler
✓ CompleteGoal → Task Graph with optimization and caching
Memory Engine
✓ Complete10 memory types with full lifecycle management
Skill Engine
✓ CompleteComposition, validation, built-in templates
Tool System
✓ CompleteCapability-based with sandboxed execution
Model Routing
✓ CompletePolicy-driven with privacy gates
Genome Versioning
✓ CompleteDiff, branch, rollback, reproduce, lineage
Benchmark Engine
✓ CompleteMindBench with 20 metrics and provenance
Ollama Runtime
⟳ In ProgressModel discovery, loading, generation
MLX Runtime
⟳ In ProgressApple Silicon optimized inference
llama.cpp Runtime
⟳ In ProgressGGUF models with quantization
MicroMind Experiment 001
○ PlannedA-K comparison: 0.8B variants vs 2B/4B raw
Foundation Stabilization
- Fix TS strictness issues
- CI/CD with build order
- Pre-commit hooks
Mind Runtime Hardening
- E2E task execution
- Memory persistence
- Skill/tool composition
Model/Provider Integration
- Ollama integration
- MLX for Apple Silicon
- llama.cpp server
- Local model benchmarks
MicroMind Experiment 001
- Run A-K comparison
- Publish results
- Analyze efficiency
First Evolution Demo
- Identify weakness
- Generate candidates
- Sandbox + benchmark
- Human approval → promote
Explore the Full Darwin Specification
Read the complete technical specification, architecture diagrams, and implementation details.