// AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
Use when working with a SwarmVault knowledge vault (raw/, wiki/, swarmvault.schema.md). Establishes schema-first conventions and prefers graph queries over broad search.
Manage your SwarmClaw agent fleet — agents, tasks, chats, chatrooms, goals, schedules, memory, wallets, connectors, autonomy, and 40+ more command groups. Use when asked to dispatch work, check agent status, coordinate multi-agent work, run diagnostics, manage schedules, set goals, or orchestrate across a SwarmClaw dashboard instance.
Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell. Use when: (1) building new features or apps in a separate project, (2) reviewing PRs, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit directly), reading code (use read/file tools), or work inside the SwarmClaw workspace itself.
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: local git operations (use git directly), non-GitHub repos, or cloning (use git clone).
Use Google Workspace CLI (`gws`) for Drive, Docs, Sheets, Gmail, Calendar, Chat, and related Workspace API tasks.
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). Use when asked to create, generate, or edit images and a Gemini API key is available. Supports text-to-image generation, single-image editing, and multi-image composition (up to 14 images).
| name | swarmclaw |
| description | AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities. |
| metadata | {"openclaw":{"emoji":"🐝","privacyPolicy":"All data stays on the local SwarmClaw instance. Memory, workspace files, and session data are stored on the host machine. No data is sent to external services unless the agent explicitly calls an external API.","dataHandling":"Agent memory is stored locally in the SwarmClaw data directory. Workspace files are scoped per agent. Credentials are injected as environment variables and automatically redacted from tool output."}} |
| version | 2.4.1 |
| author | swarmclawai |
| homepage | https://swarmclaw.ai |
| tags | ["agents","orchestration","multi-agent","runtime","memory","delegation","skills","connectors","dreaming"] |
SwarmClaw is an AI agent runtime and multi-agent orchestration platform. It gives agents a uniform set of tools, persistent memory, connector integrations, and the ability to delegate work to other agents.
Website: https://swarmclaw.ai
Docs: https://swarmclaw.ai/docs
GitHub: https://github.com/swarmclawai/swarmclaw
npm: npm install -g swarmclaw
Every agent has access to these core tools. They cover the full range of agent capabilities.
| Tool | Purpose | When to Use |
|---|---|---|
| files | Read, write, edit, list, search files | Any file operation on the workspace filesystem |
| execute | Run bash scripts (sandboxed or host) | Shell commands, curl, data processing, package management |
| memory | Store and retrieve persistent knowledge | Facts, preferences, decisions that should survive across sessions |
| platform | Tasks, communication, delegation, projects | Coordinating with humans and other agents |
| browser | Control a headless browser | Interactive web pages, JavaScript-rendered content |
| skills | Discover and load skill documentation | Learning how to use tools, APIs, or workflows |
| Task | Tool |
|---|---|
| Edit a source file | files (edit action) |
| Run tests | execute |
| Call a REST API (JSON) | execute (curl) |
| Scrape a dynamic web page | browser |
| Remember a user preference | memory |
| Ask the user a question | platform (communicate.ask_human) |
| Send a Slack message | platform (communicate.send_message) |
| Hand off work to another agent | platform (communicate.delegate) |
| Find out how a tool works | skills (read action) |
Credentials are configured per agent in the SwarmClaw UI. They are:
execute tool runs (e.g., $OPENAI_API_KEY, $GITHUB_TOKEN)<PROVIDER>_API_KEY or custom names set in the credential configYou never need to ask the user for API keys directly. If a credential is configured, it's available as an env var. If it's not configured, tell the user which credential to add in the agent settings.
Skills are markdown files that teach agents how to use tools, APIs, and workflows. They are documentation, not executable code.
{ "tool": "skills", "action": "list" }
{ "tool": "skills", "action": "read", "name": "tools/files" }
{ "tool": "skills", "action": "search", "query": "github pr" }
skills/ -- built-in skills shipped with SwarmClawdata/skills/ -- user-created skills added at runtimeAgents have persistent memory across sessions:
Agents with dreaming enabled automatically consolidate memories during idle periods. You can also trigger a dream manually:
{ "tool": "memory", "action": "list", "category": "dream_reflection" }
Use the platform API to trigger a dream cycle:
{ "tool": "execute", "command": "curl -s -X POST http://localhost:3456/api/memory/dream -H 'Content-Type: application/json' -d '{\"agentId\":\"YOUR_AGENT_ID\"}'" }
Dream cycles produce dream_reflection and consolidated_insight memories that help maintain a clean, coherent memory store over time.
Agents can delegate work to other agents:
agents.list to discover available agents and their specializationsAgents can communicate through external platforms:
platform tool with communicate.send_messageAgents can also use tools served by external Model Context Protocol servers:
https://swarmdock-api.onrender.com/mcp and just needs the Bearer header (generate a key and register an agent at swarmdock.ai/mcp/connect). See docs/mcp-servers.md for the full workflow./workspace/... paths are resolved to the workspace root automatically$WORKSPACE env var points to the workspace root in execute tool runsLoad skills before unfamiliar operations. A 30-second skill read prevents minutes of trial and error.
Use the right tool for the job. Don't use execute with echo > file.txt when files write action is cleaner. Don't use browser when curl in execute suffices.
Store important context in memory. If you learn something that would help in future sessions (user preference, project convention, API quirk), store it immediately.
Ask rather than guess. When genuinely uncertain about user intent, use communicate.ask_human. A brief clarification is better than wasted work on the wrong approach.
Delegate when appropriate. If another agent is better suited for a subtask, delegate. Check agents.list to know what's available.
Be explicit about what you're doing. When running commands, editing files, or making decisions, explain your reasoning. Transparency builds trust.
Respect file access boundaries. Stay within the workspace unless the agent has machine-scope access. Never write to system directories.
Handle errors gracefully. When a tool call fails, read the error message, diagnose the issue, and retry with a corrected approach. Don't repeat the same failing call.