kimi agents

30 tagged kimi, measured the same way as everything else here.

Browse within: gemini 9deepseek 8GLM 7copilot 7minimax 7

orchestrator

01

openinterpreter/openinterpreter

Agent

Agent "orchestrator" from openinterpreter/openinterpreter, covering user updates spec, reviews and general guidelines.

68k 12d ago A 0 tokens copy · 100% Apache-2.0

api-builder

02

happier-dev/happier

Agent Cursor

This legacy agent file is disabled. Use AGENTS.md as the canonical instruction source.

1.6k 2d ago A 0 tokens original MIT

e2e-tests-engineer

03

happier-dev/happier

Agent Claude Code

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

1.6k 2d ago A 24 tokens original MIT

happier-dev/happier

Agent

This repo (happier-dev) is a hstack project. Edison must be invoked via the hstack wrapper so stack/worktree context is enforced.

1.6k 2d ago A 0 tokens original MIT

kimi-pursue

05

linxule/kimi-plugin-cc

Agent

Use this agent ONLY when the user has explicitly asked Kimi to pursue a stated objective AUTONOMOUSLY across multiple turns (experimental goal mode) — a multi-step task the user wants Kimi to drive to completion on its own, not a single bounded edit. This is the plugin's highest-autonomy surface: WRITE-CAPABLE…

37 3d ago A 181 tokens original Apache-2.0

kimi-swarm-write

06

linxule/kimi-plugin-cc

Agent

Use this agent ONLY when the user has explicitly asked Kimi to make EDITS across MANY disjoint targets IN PARALLEL (a write fan-out) — e.g. "apply this same change to every handler, in parallel" or "fan out these independent edits across these N files." Requires BOTH signals: many independent WRITE targets AND…

37 3d ago A 224 tokens original Apache-2.0

kimi-swarm

07

linxule/kimi-plugin-cc

Agent

Use this agent ONLY when the user has explicitly asked for a READ-ONLY review fanned out in PARALLEL across many independent targets (files, modules, or questions) at once — a user-scoped whole-directory or repo-wide audit where one subagent per target is the point. Requires BOTH signals: many independent targets AND…

37 3d ago A 188 tokens original Apache-2.0

local-agents

10

feimacode/feima-copilot-llms-extension

Agent

Interactive coding-agent sessions that run inside VS Code on your computer and use the current project, files, configured models, extensions, and MCP servers.

5 5d ago A 33 tokens original MIT

kimi-reasoner

11

satasuk03/kimi-plugin-cc

Agent

Proactively use for deep reasoning, architecture tradeoffs, hard debugging analysis, or research that should stay read-only and be handed to Kimi through the shared runtime.

2 1mo ago A 37 tokens original MIT

kimi-worker

12

satasuk03/kimi-plugin-cc

Agent

Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, or should hand a substantial coding, exploration, or implementation task to Kimi through the shared runtime.

2 1mo ago A 39 tokens original MIT

kimi-rescue

13

kkk0913/kimi-plugin-cc

Agent

Proactively use when Claude Code should hand a task to Kimi for a second opinion, deeper investigation, or delegation of coding work through the kimi-cli Wire runtime.

2 3mo ago A 36 tokens

domain

14

ztemerbekov/a1-yandex-kit-skills

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

0 9d ago A 0 tokens copy · 77% MIT

triage-labels

16

ztemerbekov/a1-yandex-kit-skills

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

0 9d ago A 0 tokens copy · 81% MIT