Converge Core
A correctness-first, context-driven multi-agent runtime library.
Overview
Converge Core provides the foundational runtime for building systems where:
- Context is the API — Agents collaborate through shared data, not direct calls
- Convergence is mandatory — Execution proceeds until a fixed point is reached
- Correctness over availability — Wrong answers are worse than no answers
Core Concepts
Context
The shared, typed, evolving state of a job. Context is append-only in meaning and provides the only communication channel between agents.
Agents
Capabilities that read context and emit effects. Agents never call each other directly—all communication happens through context.
Engine
The convergence loop that coordinates agents, merges effects, and detects when execution has reached a fixed point.
Convergence
Execution halts when the context reaches a stable state (no new facts are added in a cycle).
Quick Start
use ;
use ;
// Create engine and register agents
let mut engine = new;
engine.register;
engine.register;
// Run until convergence
let result = engine.run.expect;
// Inspect results
assert!;
assert!;
println!;
Public API
Core Types
- [
Engine] — The convergence runtime - [
Context] — Shared job state - [
Agent] — Agent trait for implementing capabilities - [
AgentEffect] — Buffered output from agents - [
Fact] — Typed facts added to context - [
ProposedFact] — LLM suggestions requiring validation
Guarantees
- Determinism: Same input → same output
- Termination: Budgets prevent infinite loops
- Isolation: Agents never call each other
- Auditability: All changes are traceable
Documentation
For detailed API documentation, see docs.rs/converge-core.
For high-level architecture and design principles, see the public documentation.
License
MIT