Multi-Agent agents

1,200 tagged Multi-Agent, measured the same way as everything else here.

Browse within: Orchestration 119agent-teams 75agentic-coding 71autonomous-coding 61agentic-skills 59claude-code-plugins 59claude-code-skills 57claude-code-subagents 57agent-orchestration 49agentic 48Autonomous Agents 44agent-framework 43bun 40opencode 40

crow

193

nayasuda/phantom-template

Agent Gemini CLI

A debugging specialist that examines errors, logs, and stack traces to find likely causes and suggest fixes.

6 6mo ago A 164 tokens original MIT

mona

194

nayasuda/phantom-template

Agent Gemini CLI

A task-management and code-review agent that breaks complex work into steps and directs team members. It is designed for the Phantom project and can also decide whether an extension is needed.

6 6mo ago A 260 tokens original MIT

queen

195

nayasuda/phantom-template

Agent Gemini CLI

A Japanese-speaking project coordinator and quality reviewer for a development team. It plans work, checks results, tracks progress, updates project statuses, and can suggest turning repeated successful work patterns into reusable skills.

6 6mo ago A 271 tokens original MIT

orra

196

bjornj12/Orra-mcp

Agent

Part of orra

Orra — standing AI orchestrator for multi-worktree development. Rides on the Claude Code Agents View. Scans worktrees via orrascan (daemon roster ⨝ git), triages blocked bg agents, spawns helpers via orraspawn (which calls claude --bg), and runs a directive-driven heartbeat loop.

5 2mo ago B 69 tokens original MIT

adrian

197

adriancarriger/lambda

Agent Claude Code

Blocks until a tmux pane is done (pattern match, shell idle, or output idle). Use for any wait that takes more than a few seconds.

5 6mo ago A 34 tokens original MIT

boualam

198

adriancarriger/lambda

Agent Claude Code

Handles routine code quality tasks (linting, formatting, type checking) and trivial busywork. Runs iteratively until all checks pass. Use for cleanup tasks you don't want cluttering your main context.

5 6mo ago A 43 tokens original MIT

_protocol

199

justinjdev/fellowship

Agent

Part of fellowship

Canonical spec for how fellowship agents deliver reports and respond to lifecycle events via SendMessage.

5 20d ago A 0 tokens original Apache-2.0

balrog

200

justinjdev/fellowship

Agent

Part of fellowship

Adversarial validation agent. Spawned by quest between Implement and Review phases. Analyzes the quest diff for failure modes, writes targeted test cases, runs them, and delivers a severity-ranked findings report. Critical/High findings must be addressed before the Review gate opens.

5 20d ago A 58 tokens original Apache-2.0

palantir

201

justinjdev/fellowship

Agent

Part of fellowship

Background monitor during fellowship execution. Watches quest progress via task metadata, detects stuck quests, scope drift, and file conflicts. Spawned by Gandalf alongside quest teammates. Reports issues to the lead via SendMessage.

5 20d ago A 46 tokens original Apache-2.0

JairoTorregrosa/jaiskills

Agent

Part of jaiskills

Knowledge search agent for insistir multi-agent orchestration. Searches docs/solutions/ for past solutions relevant to a query using grep-first strategy with parallel keyword searches including synonyms. Read-only — cannot edit, write, or execute commands. Do NOT use directly — spawned by insistir skill orchestration.

5 3d ago A 68 tokens original MIT

insistir-researcher

203

JairoTorregrosa/jaiskills

Agent

Part of jaiskills

Research agent for insistir orchestration. Researches best practices, framework documentation, and codebase patterns. Read-only — cannot edit or write files. Do NOT use directly — spawned by insistir skill orchestration.

5 3d ago A 50 tokens original MIT

insistir-reviewer

204

JairoTorregrosa/jaiskills

Agent

Part of jaiskills

Cross-review agent for insistir multi-agent orchestration. Reviews another agent's implementation and sends structured findings to the lead. Read-only — cannot edit or write files. Can run verification commands (tests, typecheck, lint) via whitelisted Bash. Enforces quality without gatekeeping. Do NOT use directly …

5 3d ago A 76 tokens original MIT

reviewer

205

5uck1ess/devkit

Agent

Part of devkit

Dispatched by tri-review, mega-pr, and pr-ready workflows to perform an independent code review or to classify unresolved PR review comments into codefix, stylenit, question, falsepositive, or outofscope. Read-only; returns findings and classifications.

5 14d ago A 64 tokens original MIT

security-auditor

206

5uck1ess/devkit

Agent

Part of devkit

Dispatched by tri-security, audit, and pr-ready workflows to audit code for vulnerabilities across injection, auth, secrets management, dependencies, and unsafe patterns. Read-only; ranks findings by severity and exploitability with concrete citations.

5 14d ago A 54 tokens original MIT

test-writer

207

5uck1ess/devkit

Agent

Part of devkit

Dispatched by the test-gen workflow to generate tests for a target file or module, then iterate on failing tests until they pass. Reads source directly, matches the repo's existing test conventions, and emits test files the parent step runs.

5 14d ago A 53 tokens original MIT

critic

208

kengo006/alexandria

Agent

Blind-review critic subagent, spawned by the Writer after a draft exists. Pre-commits evaluation standards from the brief before reading the draft; criticises from three angles; lists the draft's negative universals with where to overturn them; anti-sycophancy enforced. Points at problems; never rewrites. Read-only.

5 10d ago A 68 tokens original MIT

searcher

209

kengo006/alexandria

Agent

Vault searcher subagent, spawned by the Writer. Given a passage or search request, finds relevant sources and returns verbatim quotes read from the source PDFs with real page numbers, four-layer verified. Read-only.

5 10d ago A 46 tokens original MIT

converse

210

zookanalytics/gc-toolkit

Agent

You work visits: filed requests, each one asking for a bounded sitting of a dialogue about one subject bead. The request is not the sitting — you re-check the premise it was filed on first, and only a visit that still needs a human becomes one. For those you prep, hold for the operator, record the outcome to the…

5 5d ago A 0 tokens original MIT

keeper

211

zookanalytics/gc-toolkit

Agent

You are the gascity-keeper — the operator's conversational front-end for the gascity rig's upstream lifecycle. You know.

5 5d ago A 0 tokens original MIT

mechanik

212

zookanalytics/gc-toolkit

Agent

You are the operator's specialist in how this city works — the standing conversation for understanding, diagnosing, and improving gc-toolkit and Gas City behavior. You maintain and evolve how the city operates — the formulas, the agent configurations, the dispatch patterns, the quality gates — and dispatch the…

5 5d ago A 0 tokens original MIT

blender-artist

213

bc1xxx/orchestrator-opencode

Agent

You are an expert 3D artist and technical specialist for Blender. Your role is to execute Blender operations based on precise commands received from the orchestrator translation layer. You are NOT a creative director - you are a precise executor of defined 3D tasks.

5 7mo ago A 0 tokens original MIT

orchestrator

214

bc1xxx/orchestrator-opencode

Agent

Meta-agent that plans, delegates, and aggregates work across specialist agents. Never implements directly - acts as product manager and technical lead combined.

5 7mo ago A 27 tokens original MIT

remotion

215

bc1xxx/orchestrator-opencode

Agent

You are a video creation specialist using Remotion - a React/TypeScript framework for programmatically creating videos. You build videos using code, leveraging React components to compose scenes, animations, and visual effects.

5 7mo ago A 0 tokens original MIT

AGENTS

216

Kevin-the-minion/syndicate-os

Agent

You are an OpenClaw minion in the Syndicate. This file is your standing operating contract. SOUL.md is who you are; this is how you work.

5 12d ago A 0 tokens GPL-3.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: