\n \n
\n ![\"npm](\"https://img.shields.io/npm/v/daedalus-cli?color=blue\")
![\"npm](\"https://img.shields.io/npm/dw/daedalus-cli?color=blue\")
![\"npm](\"https://img.shields.io/npm/dt/daedalus-cli?color=blue\")
![\"GitHub](\"https://img.shields.io/github/stars/bgill55/daedalus?color=blue\")
![\"Discord](\"https://img.shields.io/badge/Discord-Join%20Community-5865F2?logo=discord&logoColor=white\"){kind=icon}
![\"CI\"](\"https://github.com/bgill55/daedalus/actions/workflows/ci.yml/badge.svg\"){kind=icon}
\n ![\"Documentation\"](\"https://img.shields.io/badge/docs-GitHub%20Pages-blue\"){kind=icon}
![\"License\"](\"https://img.shields.io/github/license/bgill55/daedalus?color=blue\")
![\"Node\"](\"https://img.shields.io/badge/node-%3E%3D20-brightgreen\"){kind=icon}
\n ![\"Daedalus](\"assets/cli_view.png\")
\n ![\"Daedalus](\"assets/tui_view.png\")
\n ![\"Daedalus](\"assets/webui_view.png\")
\n
\n Three Native Interfaces: Standard REPL CLI · Interactive Terminal Dashboard (TUI) · Companion Web UI (SSE Stream)\n
\n\n\n \n
\n\n---\n\n> ### Looking to build and sell your own AI CLI?\n> Check out **[Daedalus-Lite](https://bgill55.github.io/daedalus-lite/)** — the zero-dependency, rebrandable TypeScript starter template designed for developers to build, rebrand, and sell their own custom AI coding tools! [Visit Daedalus-Lite →](https://bgill55.github.io/daedalus-lite/)\n> \n> **Fun fact**: Daedalus itself was built using Daedalus-Lite as a starting point, then extended with advanced features like multi-agent orchestration, codebase indexing, and autonomous workflows. See [what's possible with Daedalus-Lite](https://bgill55.github.io/daedalus-lite/#what-is-possible) for inspiration.\n\n---\n\n## Quick Start\n\n```bash\nnpm install -g daedalus-cli\ndaedalus\n```\n\nTo launch with the interactive terminal dashboard layout:\n```bash\ndaedalus --tui\n```\n\nTo run a single autonomous task and exit (non-interactive / headless mode):\n```bash\ndaedalus --goal \"add a --dry-run flag to the build script and update the README\"\n# also: daedalus run \"...\" (alias)\n```\nThe one-shot run auto-approves plans and tool calls so it completes without waiting for stdin, then exits with the turn's result.\n\nOn first run, Daedalus scans for local LLM servers and guides you through setup. If none are found, it prompts for a remote provider.\n\nFrom source: `git clone https://github.com/bgill55/daedalus.git && cd daedalus && npm install && npm run build`\n\n---\n\n## Why Daedalus?\n\nAI assistance without:\n- Sending your code to third-party servers\n- Per-token pricing for every interaction\n- Being locked into a single provider\n- Losing conversation history between sessions\n\n---\n\n## The B.R.A.G. Architecture: Solving Long-Horizon Autonomy\n\nStandard AI coding assistants hit a performance cliff after 15–30 minutes due to **context rot** (polluted transcripts), **the regression trap** (circular repair churn), and **transcript bias** (models falsely validating their own broken output).\n\nDaedalus overcomes this with the **B.R.A.G. Framework** and the **Harness-of-Harness (HoH) Marathon Engine (`/marathon`)**:\n\n```text\n┌─────────────────────────────────────────────────────────────────────────────┐\n│ THE B.R.A.G. AUTONOMOUS FRAMEWORK │\n├─────────────────────────────────────────────────────────────────────────────┤\n│ B — BUILD : Metis Milestone DAG Task Decomposition │\n│ R — RETRIEVE : Σ-Mem & FTS5 Semantic Codebase RAG │\n│ A — AUDIT : Apollo Air-Gapped Verification & Zero-Byte Gates │\n│ G — GENERATE : Hephaestus Production Code Delivery & Stacked PRs │\n└─────────────────────────────────────────────────────────────────────────────┘\n```\n\n- **B — BUILD:** Metis decomposes high-level goals into an ordered milestone Directed Acyclic Graph (DAG), documenting progress in a live `MARATHON_ROADMAP.md` to prevent out-of-order execution and infinite loops.\n- **R — RETRIEVE:** $\\Sigma$-Mem recalls past compiler anti-patterns (`project-mem.sqlite`) and codebase symbols via FTS5 RAG to inject hyper-targeted local context and prevent repeating past mistakes.\n- **A — AUDIT:** Apollo operates in an **air-gapped, isolated LLM context** (zero coder transcript leakage), enforcing **Deterministic Pre-LLM Gates** (instantly rejecting 0-byte stubs) and executing hard git rollbacks (`git reset --hard`) on regression loops.\n- **G — GENERATE:** Hephaestus delivers production code, mints git checkpoints (`daedalus-checkpoint/m-*`), and automatically packages completed runs into verified **Stacked Pull Requests** on GitHub.\n\n> **Architecture Deep Dive:** Read the full [B.R.A.G. & Marathon Technical Whitepaper](docs/whitepaper-brag-marathon.md) and [Autonomous Case Study](docs/marathon-case-study.md).\n\n---\n\n## Features\n\n### Core\n- **Interactive Terminal Dashboard (TUI)** — premium side-by-side dashboard with real-time CPU/RAM monitor gauges, model selection overrides, and an interactive file tree to toggle prompt context dynamically.\n- **Local-first** — works entirely on your machine with local LLMs\n- **Embedded model router** — priority, round-robin, or fastest-response routing across multiple models with real-time tokens-per-second (`tok/s`) stream telemetry, plus **Multi-Model Fallback** for zero-interruption auto-failover on rate limits (429) or 5xx errors.\n- **Dynamic complexity-based routing** — classifies each task on arrival (quick/trivial → `fast` tier, heavy/multi-file → `intelligence` tier) and **re-routes on the fly** mid-task as the work evolves, with hysteresis to avoid flapping and a token budget that resets on downgrade so it never ping-pongs. Repeated tool failures trigger automatic escalation to the next model in the chain.\n- **Multi-agent orchestration** — spawns Metis (planner), Hephaestus (coder), Apollo (reviewer), Asclepius (debugger), and Mnemosyne (researcher) sub-agents — each carrying a divine callsign — with **OpenAI Swarm-Style Dynamic Handoffs (`handoff_task`)** and shared **Context Variables (`contextVariables`)** for seamless mid-turn role transfers. In single-agent REPL mode the active agent can also **auto-route** a large multi-phase task to helper agents in parallel via `route_task` (after explicit user approval through `ask_user`), so the user never has to spawn agents manually.\n- **Harness-of-Harness (HoH) Marathon Engine (`/marathon`)** — multi-day autonomous software development powered by the **B.R.A.G. framework** (Build DAGs, Retrieve memory, Audit air-gapped, Generate stacked PRs); Metis milestone DAG planning, air-gapped Apollo evaluation (isolated prompt context), git checkpoint rollbacks (`daedalus-checkpoint/m-*`), $\\Sigma$-Mem anti-pattern persistence across days, and automated **Stacked PR generation (`/marathon pr`)** on GitHub.\n- **Companion Web UI & Sovereign Mobile PWA Companion (`/webui`)** — native local HTTP, WebSocket & Server-Sent Events telemetry dashboard (`http://localhost:3888`) featuring a sleek Greek mythic dark-mode interface, real-time token streaming, Chronicles session archives, active model switcher modal, in-chat tool accordions, hover code copy, and multimodal paste/drag-and-drop. Fully installable as a mobile-first **Progressive Web App (PWA)** with offline service worker caching (`sw.js`), 48px tactile touch targets, **QR Code Remote Pairing (`/api/qr`)** over LAN/Tailscale, and real-time **Milestone Push Notifications**.\n- **Autonomous Finn Loop** — interactive requirements gathering (`/spec`), GitHub Issues tracking, background daemon execution (`daedalus --loop`), and Discord PR review webhook embeds.\n- **CaSKG Procedural Skill Graph Engine** — counterfactual-causal skill dependency graphs (`src/skills/graph.ts`) that resolve `prerequisites` and `leadsTo` relationships, retrieving **topologically sorted, compact skill bundles** to eliminate orphan execution and step thrashing.\n- **Self-Healing & Immunity Engine** — Programmatic Codebase Constitution (`src/config/constitution.ts`), default Test Suite Read-Only Lock (`*.test.ts`, vitest/jest runner configs, CI workflows), Reviewer Diff Immunity Audit Checklist (protecting against type-loosening, error-swallowing, and assertion weakening), and Self-Generated Skill Synthesis (`.daedalus/skills/drafts/`).\n- **Loop Engineering & Self-Repair** — automatic stack-aware compile/build verification checks (e.g., `npx tsc --noEmit`, `cargo check`, `go build`) with dynamic stdout/stderr feedback loops for self-repair, **Automated Workspace Rollback** to revert patches upon task failure, and **Git-Aware Smart Testing (`/test -g`)** to run only affected unit tests in < 200ms.\n- **Codebase indexing & Live Watcher** — FTS5-powered symbol search, definitions, and call-graph references across 10+ languages with background **Live File-Watcher (`/watch`)** for automatic re-indexing on save.\n- **MCP Marketplace & Explorer (`/mcp explore`)** — Model Context Protocol server marketplace with one-click installation (`/mcp install