{"slug": "swarmvault-a-lean-llm-agent-workflow", "title": "Swarmvault: A Lean LLM Agent Workflow", "summary": "Developer AnmarHani released Swarmvault, an open-source LLM agent workflow framework that uses only 13 core skills and a local folder vault system to enable spec-driven execution and parallel agent collaboration without background processes or telemetry. The MIT-licensed tool supports verified platforms including Claude Code and Codex, with best-effort support for Gemini CLI, OpenCode, Cursor, and Copilot on Linux, macOS, and WSL.", "body_md": "# Swarmvault: A Lean LLM Agent Workflow\n\n```\ngit clone https://github.com/AnmarHani/swarmvault && cd swarmvault && ./install.sh\n```\n\n## Context-First Design\n\nThe framework consists of only 13 core skills. This isn't an arbitrary number; it's what remained after stripping away overlap and redundancy. The philosophy here is that if a capability is missing, it should be a thin extension rather than a heavy new skill competing for the same context window. Every skill is modular—you can drop one into any agent's directory, and it functions independently without needing the rest of the vault.\n\n## Spec-Driven Execution\n\nInstead of relying on \"vibes\" or hopeful prompting, this follows a strict technical pipeline:\n\n1. A requirements interview that produces a real SRS.\n\n2. A design phase where decisions are formally logged.\n\n3. Tickets generated in dependency order with clear \"definition of done\" tests.\n\nA strong model audits the work against the spec at every milestone. This eliminates the \"filler\" code and fluff documentation that usually plague agent outputs.\n\n## The Vault System\n\nThe \"vault\" is simply a local folder structure:\n\n`10 Projects`\n\n`20 Memory`\n\n`30 Plans`\n\n`40 Sessions`\n\n`50 Decisions`\n\nIt uses a zero-dependency script to give agents\n\n`query`\n\n, `sync`\n\n, `claim`\n\n, and `context`\n\ncapabilities. This allows you to start a fresh session and say \"continue project X,\" and the agent picks up exactly where it left off. Because agents \"claim\" tickets, you can run multiple agents in parallel without them duplicating work.## Model Routing and Compatibility\n\nThe system includes an optional orchestrator that distributes tasks across different platforms ([Claude](/en/tags/claude/) Code, Codex, Cursor) based on model strengths and usage limits. Adding a new CLI is handled via a launch-command template rather than a complex plugin system.\n\n**Current Support:**\n\n**Verified Platforms:** Claude Code, Codex**Best-effort Platforms:**[Gemini](/en/tags/gemini/)CLI, OpenCode, Cursor, Copilot** OS:**Linux, macOS, WSL (Native Windows is best-effort)\n\nThere are no background processes, no telemetry, and no hosted services—just plain Markdown files on your disk under an MIT license.\n\n```\nhttps://github.com/AnmarHani/swarmvault\n```\n\n[Next phi-leak-guard: A Practical Tutorial for PHI Leak Detection →](/en/threads/3691/)", "url": "https://wpnews.pro/news/swarmvault-a-lean-llm-agent-workflow", "canonical_source": "https://promptcube3.com/en/threads/3702/", "published_at": "2026-07-26 14:01:25+00:00", "updated_at": "2026-07-26 14:08:46.196880+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "large-language-models"], "entities": ["AnmarHani", "Swarmvault", "Claude Code", "Codex", "Gemini CLI", "OpenCode", "Cursor", "Copilot"], "alternates": {"html": "https://wpnews.pro/news/swarmvault-a-lean-llm-agent-workflow", "markdown": "https://wpnews.pro/news/swarmvault-a-lean-llm-agent-workflow.md", "text": "https://wpnews.pro/news/swarmvault-a-lean-llm-agent-workflow.txt", "jsonld": "https://wpnews.pro/news/swarmvault-a-lean-llm-agent-workflow.jsonld"}}