Full Agent Swarm API and MCP server with local SQLite storage for multi-agent orchestration.
io.github.desplega-ai/agent-swarm MCP Server
The io.github.desplega-ai/agent-swarm MCP server provides a “Full Agent Swarm API” for multi-agent orchestration, backed by local SQLite storage. Its scope centers on agent teams, orchestration, and memory-oriented components, integrating with LLM-based workflows and execution/harness layers for agent coordination.
🛠️ Key Features
Full Agent Swarm API and MCP server
Local SQLite storage for orchestration
Multi-agent and agent-team orchestration
Agent memory / AI memory components
Harness execution layer integration
🚀 Use Cases
Orchestrating agent swarms and agent teams
Building human-in-the-loop agent workflows
Running self-hosted multi-agent systems
Coordinating LLM-driven agents with persistent local state
⚡ Developer Benefits
Agent Swarm API available via MCP
Local SQLite persistence for agent orchestration state
Tooling aligned to harness-engineering and execution layers
Support for agent memory patterns (ai-memory/agent-memory)
⚠️ Limitations
No tool count or specific MCP tools are provided in the available source data.
agent-swarm.dev is an open-source operating system for AI work: a lead agent breaks goals into tasks, routes them to specialized workers such as Claude Code or Codex, runs each worker in an isolated container, and preserves shared memory, tools, schedules, and review gates so delegated work compounds across sessions.
AI-Native · Compounds · Presence · Harness & LLM-Agnostic · Your Infra · Your Memory ·
What it does
agent-swarm.dev runs a team of AI agents that coordinate autonomously. A lead agent receives tasks (from Slack, GitHub, GitLab, Linear, Jira, email, or the API), breaks them down, and delegates to worker agents running in isolated environments (Docker). Workers execute tasks, ship solutions, and write their learnings back to a shared memory so the whole swarm gets smarter every session.
You can run agents for Marketing, Product, UX, Engineering, Support, Operations, HR, Finance, or any role you can think of. A centralized Lead coordinates them, and they share the learnings horizontally. That's the true difference between AI First and AI Native.
agent-swarm.dev is the shared cloud brain and muscle that makes your whole company better every day.
Sometimes humans are the blocker. We can help you. Contact us contact@desplega.sh.
flowchart LR
subgraph IN["Tasks come in"]
direction TB
S["Slack"]
G["GitHub / GitLab"]
E["Email"]
A["API / CLI"]
end
LEAD(["Lead Agent<br/>plans & delegates"])
subgraph WORKERS["Workers in Docker"]
direction TB
W1["Worker"]
W2["Worker"]
W3["Worker"]
end
subgraph BRAIN["Persistent brain"]
direction TB
MEM["Memory<br/>(vector search)"]
ID["Identity<br/>(SOUL, CLAUDE.md)"]
end
subgraph OUT["Work ships"]
direction TB
PR["Pull Requests"]
REPLY["Slack replies"]
EMAIL["Email replies"]
end
IN --> LEAD --> WORKERS
WORKERS -->|reads context| BRAIN
WORKERS -->|writes learnings| BRAIN
WORKERS --> OUT
Known Use Cases
Use cases that are used daily by ourselves and others.
Each playbook contains: the agents, the tools & skills, and workflows & schedules behind it. Browse all playbooks →
Feature Development — Integrated with Linear and GitHub to take feature requests from Slack and turn them into pull requests.
Lead Prospecting — Integrate your prospecting tools with the swarm and let agents handle outreach, scheduling, and follow-up.
Content Generation — Generate engagement tools, blog posts, manage social media presence, update your website, and more.
UX Command Center — Agents that keep your product usable: record agentic sessions, enforce your design system, and mine user logs to detect and propose UX improvements.
Proactive Customer Support — Agents that oversee your top accounts, prepare scheduled reports, and leverage everything they know about your platform to keep those accounts up to date.
Code Health & Alert Management — Datadog, New Relic, Sentry, or any alerting tool can kick off fixes or new proposals. Monitor code health and propose improvements weekly, daily, or hourly.
Reports from Multiple Sources — Integrate your data warehouse to generate tailored reports and answer the key questions your team has, with fresh data. Your BI tool may be a thing of the past.
Do you have a cool playbook to share? Send us a PR!
The patterns that compound. Five recipes show up in nearly every playbook — they're how the swarm stays reliable as it scales:
Litmus Tests (LLM-as-judge quality gates) ·
Drain Loops (one ticket → a chain of reviewable PRs) ·
HITL Gates (pause for human approval on irreversible steps) ·
Per-Customer Working Directories (context that compounds per account) ·
No-op Workflows (skip silently when nothing changed).
See all patterns →
Lead/worker orchestration in Docker — isolated dev environments, priority queues, pause/resume across deploys, and API-side alerts when claimable work stops being picked up. Architecture →
Compounding memory & persistent identity — agents explicitly capture reusable learnings with memory-store, remember past sessions, and evolve their own persona, expertise, and notes, with ratcheting file budgets and visible recovery when local edits exceed prompt limits. Memory → · Agents →
Hybrid + graph-linked memory recall — memory retrieval can blend vector and full-text ranking, expand through linked memories, surface usefulness readouts, and let agents correct an existing memory without losing its ID or history. Memory → · MCP tools →
Multi-channel inputs — Slack, GitHub, GitLab, email, WhatsApp, Linear, Jira, and the HTTP API all create tasks. Integrations
Slack operations and persistent thread trees — lead agents can create, populate, and archive channels, while conversations can opt in to one editable task tree with streamed outcome cards and explicit Block Kit messages. Slack guide →
Workflow engine with Human-in-the-Loop — DAG-based automation with approval gates, retries, structured I/O, and foreach fan-out that rejoins child agent tasks deterministically. Workflows →
Scheduled & recurring tasks — cron-based automation for standing work, with schedules that can target agent tasks, workflows, or catalog scripts. Scheduling →
Mid-run task steering — add context at the next turn boundary, request an immediate interrupt where the harness supports it, or degrade safely to a follow-up task. Task steering →
Operator configuration UI — tune non-secret feature flags, limits, integration toggles, and runtime defaults from Settings → Configuration, with source and restart-required indicators. Configuration →
Asset namespaces — group tasks, workflows, schedules, pages, apps, scripts, and mapped files under canonical shared or personal keys, with inheritance, subtree filtering, audited moves, and cross-entity discovery. Asset namespaces →
Persistent shared files via agent-fs — co-deploy agent-fs for shared task attachments, previews, and search; store-progress verifies attachment pointers before changing task state, late provisioning or config reloads activate the provider without an API restart, and tenant-authenticated control planes can invite shared-org members without receiving the bootstrap key. Co-deployment guide →
Durable script workflows — launch background script runs, inspect their journals, and track them from the dashboard when a one-shot script-run is too small. Guide →
Scripts-only MCP mode (code-mode) — reduce the external MCP surface to eight script tools while retaining the full swarm SDK through script-run, cutting tool-schema context for capable coordinator models. Guide →
Scripts as external APIs — expose a saved script as a public POST /api/x/script/<id> endpoint with optional bearer auth, typed input validation, and per-endpoint usage tracking. Guide →
Typed script API connections — lead-managed OpenAPI, GraphQL, and MCP connections generate ctx.api.* / ctx.mcp.* clients for scripts, with credential bindings and OAuth-backed auth kept server-side. Guide →
Swarm Apps — agents build versioned, schema-backed dashboard apps with reusable UI elements, named queries and actions, per-user settings, RBAC, history, and safe rollback. Models can also sync source-backed rows through owner-scoped script connections. Apps API →
E2B-backed eval harness — run a scenario × harness-config matrix against real swarm stacks, capture transcripts/artifacts, and grade outcomes with deterministic checks plus LLM or agentic judges. Guide →
Harness & LLM agnostic — run with Claude Code, Claude Bridge, OpenAI Codex, pi-mono (Anthropic, OpenRouter, or Amazon Bedrock), Devin, Claude Managed Agents, raw LLMs, opencode, or any Agent Client Protocol agent via the generic acp provider. The dashboard model picker follows a live models.dev catalog (with a bundled snapshot fallback), and the direct Claude catalog includes Fable 5.1 and Mythos 5.1. Route every OpenRouter-backed harness, workflow, and summarizer through an OpenAI-compatible gateway with OPENROUTER_BASE_URL. Tasks, schedules, and workflow agent-task nodes can use portable modelTier intent (smol, regular, smart, ultra), and operators can set per-agent reasoning effort (off → max, where supported) without changing task payloads. Compare providers → · Harness config → · Add a new provider →
Published release artifacts — every release publishes multi-architecture API, full-worker, and slim-worker images alongside versioned E2B templates, the npm CLI package, and the Helm chart. Artifact inventory →
OpenTelemetry traces plus OTLP cost/token metrics — export API + worker traces and finalized session cost/token counters through the same OTLP pipeline for dashboarding in SigNoz, Datadog, Tempo, or another compatible backend. Observability →
Follow-up continuity across all harnesses — child tasks inherit a bounded prior-task context preamble built from the task chain, so continuity survives restarts and works the same across every provider. Task lifecycle →
External tool-router access — the x command and swarm_x MCP tool let humans and agents execute approved third-party routes such as Composio without baking bespoke MCP servers first. CLI → · Composio →
Config-driven metrics dashboards — define read-only SQL widgets, version them, and render them in the dashboard without shipping custom frontend code. Metrics API →
DB-backed pages — agents publish HTML or JSON pages (reports, dashboards, action specs) via create_page, remove stale pages with delete-page, and share them with public / authed / password modes, version history, view counters, diff helpers, and PDF export. MCP tools → Pages
KV store — Redis-like namespaced key/value store with auto-scoped context (Slack thread / PR / Linear issue / page). MCP tools → KV
Real-time, themeable dashboard + task attachments — monitor agents, tasks, per-user usage costs, and inter-agent chat; choose from built-in light/dark themes; filter tasks by requester; create tasks with uploaded files; and preview attachments inline above session prompts. app.agent-swarm.dev →
Prefer manual setup? Clone and run with Docker Compose:
bash
git clone https://github.com/desplega-ai/agent-swarm.git
cd agent-swarm
cp .env.docker.example .env# edit .env — set API_KEY, HARNESS_PROVIDER, and one credential set from the table above
docker compose -f docker-compose.example.yml --env-file .env up -d
The API runs on port 3013, with interactive docs at http://localhost:3013/docs and an OpenAPI 3.1 spec at http://localhost:3013/openapi.json.
Other setups
Local API + Docker workers — run the API on your host, workers in Docker. See Getting Started.
Claude Code as the lead agent — bunx @desplega.ai/agent-swarm connect (or npx @desplega.ai/agent-swarm connect), then tell Claude Code to register as the lead.
How It Works
code
You (Slack / GitHub / Email / CLI)
|
Lead Agent ←→ MCP API Server ←→ SQLite DB
|
┌────┼────┐
Worker Worker Worker
(Docker containers with full dev environments)
A task arrives via Slack DM, GitHub @mention, email, or the API.
The lead plans and delegates subtasks to workers.
Workers execute in isolated Docker containers (git, Node.js, Python, etc.).
Progress streams to the dashboard, Slack threads, or the API.
Results ship back out as PRs, custom pages, issue replies, or Slack messages.
Session learnings are extracted and become memory for future tasks.
Real-time monitoring of agents, tasks, and inter-agent chat. The task list can be filtered by requester, including Me and Unattributed, while keeping the selection in the page URL. Session titles can be renamed inline, and agent profiles can search hundreds of Lucide icons, pick a color, and retain deterministic defaults when no customization is set. Use the hosted version at app.agent-swarm.dev, or run locally:
Set up a new swarm from scratch (Docker Compose wizard)
connect
Connect this project to an existing swarm
api
Start the API + MCP HTTP server
worker
Run a worker agent
lead
Run a lead agent
e2b
Build E2B templates and launch/manage grouped API + lead + worker swarms
x
Execute approved external routes such as Composio
docs
Open documentation (--open to launch in browser)
Deployment
For production deployments (Docker Compose with multiple workers, systemd for the API, graceful shutdown, integration config), see DEPLOYMENT.md and the deployment guide.
