elizaOS/eliza
by elizaOS
Description
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.
Summary
Feature-rich multi-agent framework (30K+ LOC core, 28 files traced). Steal: BM25+vector action filtering (solves >15 tool confusion), provider system (text+values+data triple, parallel exec), sandbox ...
Steal Patterns
Token-based budgeting (not count-based) with 1.3x formatting overhead
Per-message size cap
Auto-triggers session compaction when budget exceeded
Separates action results from dialogue messages
Outbound: URL/headers/body → replace stok_ tokens with real values
Execute actual HTTP request
Inbound: text responses → replace real values with stok_ tokens
Audit callback on every replacement
Fail-closed mode: unresolvable tokens → throw
Longest-first replacement to prevent partial matches
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.
openai/swarm
openai
- **Core library:** 4 files, 507 lines total
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.