By SwarmDo
MetaHarness integration for swarmdo — surfaces score/genome/mint/mcp-scan/threat-model via skills; pairs with @metaharness/router (ADR-148/149) for cost-optimal model routing; honors ADR-150's architectural constraint that MetaHarness remains an optional augmentation, never a required runtime dependency
Manage `@metaharness/darwin` bench suites — `bench create <repo>` scaffolds a JSON suite from a repo's test corpus; `bench verify <suite.json>` checks suite well-formedness. Bench suites are the fixed evaluation corpora that `harness-evolve --bench <suite.json>` scores variants against, decoupling evolution from the repo's natural tests. Degrades gracefully when @metaharness/darwin is absent.
One-command drift detection. Composes audit-list + oia-audit + audit-trend into a single primitive — finds the most recent audit in `metaharness-audit` namespace, runs a fresh audit against the current repo, diffs them via ADR-152 §3.1 similarity, and alerts when structural distance crosses `--threshold`. Iter 53 of ADR-150 deep integration.
Run `@metaharness/darwin evolve <repo>` to mutate a harness's seven policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy), sandbox-score each variant, and promote only measured wins. The model is frozen; the harness evolves. Closes the loop ADR-150 opens (score+genome describe; evolve changes). Degrades gracefully when @metaharness/darwin is absent (ADR-150 + ADR-153 architectural constraints).
7-section repo readiness report from `metaharness genome <path>`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness. Pure-read; degrades gracefully (ADR-150).
Static security scan of a harness's declared MCP surface via `harness mcp-scan <path>`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch. Exits 1 on findings at or above `--fail-on` severity.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Based on the original, hugely popular ruflo — renamed, self-contained, and MIT-licensed. Full lineage in NOTICE.
An agent meta-harness for Claude Code and Codex.
Agent = Model + Harness. The model writes; the harness gives it tools, memory, loops, sandboxes, and controls so it can actually work. Swarmdo is the harness — the execution layer around Claude Code and Codex that adds 100+ specialized agents, coordinated swarms, self-learning memory, federated comms across machines, and enterprise security guardrails. So agents don't just run, they collaborate.
One npx swarmdo init gives Claude Code a nervous system: agents self-organize into swarms, learn from every task, remember across sessions, and — with federation — securely talk to agents on other machines without leaking data. You keep writing code. Swarmdo handles the coordination.
Self-Learning / Self-Optimizing Agent Architecture
User --> Swarmdo (CLI/MCP) --> Router --> Swarm --> Agents --> Memory --> LLM Providers
^ |
+---- Learning Loop <-------+
New to Swarmdo? You don't need to learn 314 MCP tools or 26 CLI commands. After
init, just use Claude Code normally — the hooks system automatically routes tasks, learns from successful patterns, and coordinates agents in the background.
Swarmdo is now Swarmdo — named by
the upstream author, who loves Rust, flow states, and building things that feel inevitable. The "Ru" is the the upstream author. The "flo" is working until 3am. Underneath, powered byCognitum.Oneagentic architecture, running a supercharged Rust-based AI engine, embeddings, memory, and plugin system.
There are two different install paths with very different surface areas. Pick based on what you need (#1744):
| Claude Code Plugin | CLI install (npx swarmdo init) | |
|---|---|---|
| What it gives you | Slash commands + a few skills + agent definitions per-plugin | Full Swarmdo loop — 98 agents, 60+ commands, 30 skills, MCP server, hooks, daemon |
| Files in your workspace | Zero | .claude/, .swarmdo/, CLAUDE.md, helpers, settings |
| MCP server registered | No (memory_store, swarm_init, etc. unavailable to Claude) | Yes |
| Hooks installed | No | Yes |
| Best for | Try a single plugin's commands without committing to the full install | Production use — everything works as documented |
# Add the marketplace
/plugin marketplace add upstream/swarmdo
# Install core + any plugins you need
/plugin install swarmdo-core@swarmdo
/plugin install swarmdo-swarm@swarmdo
/plugin install swarmdo-rag-memory@swarmdo
/plugin install swarmdo-neural-trader@swarmdo
This adds slash commands and agent definitions only. The Swarmdo MCP server is NOT registered, so memory_store, swarm_init, agent_spawn, etc. won't be callable from Claude. For the full loop, use Path B below.
| Plugin | What it does |
|---|---|
| swarmdo-core | Foundation — server, health checks, plugin discovery |
| swarmdo-swarm | Coordinate multiple agents as a team |
| swarmdo-autopilot | Let agents run autonomously in a loop |
| swarmdo-loop-workers | Schedule background tasks on a timer |
| swarmdo-workflows | Reusable multi-step task templates |
| swarmdo-federation | Agents on different machines collaborate securely |
AI agent orchestration for Claude Code: swarm coordination, 314 MCP tools, 60+ agent types, persistent AgentDB memory with HNSW vector search, self-learning hooks, SPARC methodology, and GitHub automation
Ponytail for swarmdo — makes agents think like the laziest senior dev in the room: YAGNI, stdlib before dependencies, one line before fifty. Intensity levels lite/full/ultra plus audit, review, debt, and gain sub-skills. Vendored from DietrichGebert/sdo-ponytail (MIT).
Cross-installation agent federation with zero-trust security, peer discovery, consensus-based task routing, and per-call budget circuit breaker (ADR-097)
Self-learning vector database via npx [email protected] — HNSW, adaptive LoRA embeddings, code-graph clustering, hooks routing, brain/SONA, 103 MCP tools
ADR lifecycle management — create, index, supersede, check compliance, and link Architecture Decision Records to code via AgentDB hierarchical store + causal edges (supersedes/amends/depends-on/related)
npx claudepluginhub swarmdo/swarmdo --plugin swarmdo-metaharnessUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications