open claw agents

18 tagged open claw, measured the same way as everything else here.

Browse within: low-code 12n8n 12ai-native 5harness-engineering 5openclaw 5

task-delegator

01

freema/openclaw-mcp

Agent

Agent for delegating long-running tasks to OpenClaw. Manages async operations and monitors task progress.

183 16d ago A 26 tokens original MIT

explore

02

Timeflys2018/zeyi

Agent

Codebase explorer — answers "where is X?" / "find the code that does Y" / "list all callers of Z". Read-only grep + glob + read, no memory injection.

21 19d ago A 42 tokens original MIT

librarian

03

Timeflys2018/zeyi

Agent

External reference researcher — looks up library docs, framework conventions, OSS examples. Read-only, no memory injection. (Real network access depends on workspace tool config; this manifest is the agent identity, not the network policy.).

21 19d ago A 48 tokens original MIT

reviewer

04

Timeflys2018/zeyi

Agent

Code reviewer — analyzes diffs and source for bugs, security issues, and style violations. Read-only, no memory injection.

21 19d ago A 28 tokens original MIT

channels

05

yogasw/wick

Agent

A channel is where a message comes from. Wick agents are reachable from four channels at once.

5 4d ago A 0 tokens original MIT

providers

06

yogasw/wick

Agent

A provider type is an AI CLI: claude, codex, gemini (provider.go:36-40). A provider instance is a configured copy of one. Multiple instances per type are supported — same claude binary, different env vars (e.g. two PATs).

5 4d ago A 0 tokens original MIT

sub-agents

07

yogasw/wick

Agent

A sub-agent is another agent that your agent hands one self-contained task to, waits for, and gets an answer back from. Use it when a piece of work wants a different role — research, code review, image generation — or when the intermediate steps would flood the main conversation.

5 4d ago A 0 tokens original MIT