The open agent registry.

OpenClaw

TYPESCRIPT · v2026.3.7

Any Claws model — defaults to claude-sonnet-4-6

48.2k stars · 1.2M deploys

GeneralFlagship

The flagship general-purpose agent. Tools, memory, streaming and multi-step planning out of the box.

NanoClaw

RUST · v2026.3.4

Any Claws model — defaults to claude-haiku-4-2

31.7k stars · 840k deploys

EdgeLightweight

A featherweight runtime tuned for sub-100ms responses at the edge. Single static binary, zero deps.

OpenBot

PYTHON · v2026.2.9

Any Claws model — defaults to claude-sonnet-4-6

27.4k stars · 610k deploys

SupportChat

Conversational support agent with built-in human handoff, ticket sync and sentiment routing.

NanoBot

GO · v2026.3.1

Any Claws model — defaults to mistral-small-3

22.9k stars · 540k deploys

AutomationLightweight

Minimal task-runner for cron jobs, webhooks and background pipelines. Durable, idempotent, fast.

Any Claws model — defaults to mistral-small-3

10.7k stars · 150k deploys

AutomationScheduler

Scheduler-first agent. Durable jobs, retries with backoff, and dead-letter queues, batteries included.

Per-node model selection across any Claws model

9.4k stars · 120k deploys

WorkflowPipelines

Visual workflow agent — compose DAG pipelines of tools and models, branch on output, replay any run.

Mix-and-match per worker across any Claws model

8.1k stars · 92k deploys

Multi-AgentDistributed

Distributed swarm coordinator. Shard work across nodes with gossip state and at-least-once delivery.

Any vision model — defaults to gemini-3-flash-pre

7.6k stars · 78k deploys

BrowserAutomation

Browser & RPA automation agent. Drives the DOM with vision fallbacks for resilient web tasks.

Any Claws model — defaults to gpt-o5-mini

6.9k stars · 64k deploys

DevOpsTools

DevOps agent that lives in your terminal — runs infra tools, reads logs, and proposes safe diffs.

Any Claws model — defaults to claude-sonnet-4-6

5.8k stars · 51k deploys

SecurityCompliance

Security-first agent with PII redaction, on-prem key handling and a full, tamper-evident audit log.

OpenHands

PYTHON · v0.31.0

Any Claws model — defaults to claude-sonnet-4-6

58.4k stars · 92k deploys

AutonomousCoding

Autonomous software-engineering agent that plans, edits code, runs tests and iterates with a web UI.

AutoGen

PYTHON · v0.7.3

Any Claws model — replaces the built-in OpenAI/Azure config

36.1k stars · 71k deploys

Multi-AgentChat

Microsoft's multi-agent conversation framework, with an AutoGen Studio UI for no-code composition.

Letta

PYTHON · v0.9.4

Any Claws model — routed through our unified endpoint

17.2k stars · 41k deploys

MemoryStateful

Stateful, memory-first agents (formerly MemGPT) with a visual Agent Development Environment.

Agno

PYTHON · v2.4.1

Any Claws model — LLM class swapped at container start

26.3k stars · 48k deploys

GeneralPlatform

Full-stack agent platform (formerly Phidata) — batteries-included UI, memory, tools and knowledge.

GPT Researcher

PYTHON · v4.2.0

Any reasoning model — defaults to claude-opus-4-2

15.7k stars · 37k deploys

ResearchReports

Autonomous research agent that produces long-form, cited reports through a clean web UI.

SuperAGI

PYTHON · v0.5.0

Any Claws model — provider config injected at boot

16.9k stars · 29k deploys

AutonomousDashboard

Autonomous long-running agent runtime with a dashboard, marketplace and toolkit ecosystem.