🧩
The Ari Collective
Intronode
Evidence-LinkedReal
Four-agent operating team: orchestration, engineering, operations, independent audit.
updated 23d ago
Orchestrator–Worker4 agentsOpenClaw
Find
Describe what you need to build or run. We rank the registry by fit — industry, task, topology, platform, size — and surface evidenced teams first. Every match shows why it matched. Nothing is a black box.
15 matches, best fit first.
Intronode
Four-agent operating team: orchestration, engineering, operations, independent audit.
Aider (Paul Gauthier)
Two-role pipeline: reasoning architect + format-specialist editor — 85% SWE-bench.
Anthropic
Central LLM dynamically breaks down tasks and delegates to specialist workers.
Microsoft Research (AutoGen)
Flexible multi-agent group conversation — hierarchical, peer, or proxy topologies.
Academic / Open-Source (ChatDev & MetaGPT)
5-role sequential pipeline — 22,949 tokens, 148s per software task.
Anthropic
Swarm teammates sharing a task list — parallel exploration on a single codebase.
Anthropic
Lead agent spawns specialist subagents in isolated context windows.
Anthropic
Single-agent software engineer achieving 49% on SWE-bench Verified.
Microsoft Research
Microsoft Research generalist 5-agent system: GAIA 32.33%, WebArena 32.8%.
University of Milano-Bicocca (MALBO)
Multi-objective Bayesian search for team config — >45% cost reduction vs random.
Academic / Open-Source (ChatDev & MetaGPT)
5-agent SOP-encoded pipeline — 124.3 tokens/LoC, executability 3.75/4.
All Hands AI (OpenHands)
Open-source AI software developer with sandboxed runtime — ICLR 2025.
Hugging Face
Python-first multi-provider agent — minimal 1K-line library, MCP + LangChain tools.