openai/swarm
by openai
Description
- **Core library:** 4 files, 507 lines total
Summary
Canonical 507-LOC reference implementation for agent handoffs. Two primitives—Agent + Handoff—create stateless client-side orchestration loop. Steal: function-return-as-handoff (validated across 4 rep...
Steal Patterns
function-return-as-handoff (zero-config agent switching)
context_variables injection via `co_varnames` introspection
`execute_tools=false` for external tool execution
mock client testing pattern
and the "routines as agents" philosophy.
** This is trivially implementable and immediately useful
** The `delim` pattern is essential for real-time multi-agent UIs
** This sequential response mock pattern is perfect for testing Forge agent handoffs
Tags
Related Tools
parruda/swarm
parruda
A mature Ruby multi-agent orchestration framework (~49.3K LOC across 259 non-test source files, 4 gems: SwarmSDK, SwarmCLI, SwarmMemory, ClaudeSwarm-legacy) with sophisticated plugin architecture, 6-pass agent initialization, lazy delegation, Fiber-based circular dependency detection, comprehensive hooks system (13 events, 6 result actions), composable swarms, persistent memory with semantic search, context compaction, and state snapshot/restore. The most architecturally complete open-source agent framework analyzed to date.
elizaOS/eliza
elizaOS
Feature-rich multi-agent framework with excellent plugin architecture, provider-based context injection, BM25 action filtering, and sandbox security — but sprawling complexity dilutes the core.
JackChen-me/open-multi-agent
JackChen-me
open-multi-agent is a clean, well-typed TypeScript multi-agent framework that validates the coordinator-as-LLM pattern for auto-task-decomposition. Its architecture is lateral to Forge's SOP-driven execution — different paradigm, not better/worse.