🚀 What is Godcoder?

Godcoder is a local-first, fully open-source AI coding agent that runs as a native desktop app. Unlike cloud-based tools, your source code never transits a vendor backend — API requests go straight from your machine to whichever model provider you configure.

Your Machine ──► Model Provider (OpenAI / Anthropic / Any OpenAI-compatible API)
     ▲
     │  (no middleman, no cloud backend, no data lock-in)
     │
  Your Code

Reimagined from the ground up. The original 2024 autonomous-dev pipeline is frozen under v1/ — preserved, not maintained.

✨ What Godcoder Can Do

🔁 Self-optimizing AI Agent Harness

Harness mode turns Godcoder loose on its own agent harness. Pick Harness
in the new-session composer and press start — no prompt to type and no folder to
choose. On launch the agent sets up a contained sandbox: it creates a
dedicated harness-build/ folder, opens it in your system file explorer, and
confines all of its new work there — reading the rest of the repo for reference
but never rewriting it. It then runs a full-autonomy, real-time improvement loop:

route → plan → execute → evaluate → log → optimize → repeat

Each iteration makes one decisive change, verifies it with the project's own
checks, keeps it only if it's an improvement, and records the outcome so the
harness compounds knowledge over time and biases toward higher-success
approaches. Like Freestyle, every tool call is auto-approved (you confirm the
first time).

The loop is backed by the self-optimizing-harness default skill
(crates/agent/default-skills/) and a
ResearchSwarm bridge
(third_party/ResearchSwarm-master/godcoder_harness.py)
exposing route / log / recall / optimize over a persistent memory store,
so lessons from past runs rank and steer future iterations.

🏗️ Architecture

Godcoder is built on a pure-Rust agent core with the desktop app as a thin adapter on top:

apps/desktop/          Tauri 2 + React desktop app (thin adapter)
crates/
  agent/               Rust agent core — the harness (loop, tools, modes, subagents)
  git-ops/             Checkpoint / diff / restore over the working tree
services/
  context-engine/      Optional Go indexing service (tree-sitter → Qdrant + FalkorDB + BM25)
third_party/
  ResearchSwarm-master/  Self-optimizing harness memory + bridge (Harness mode)
v1/                    Legacy 2024 codegen pipeline — frozen

See ARCHITECTURE.md for a deep-dive on how these fit together.

🔥 Two Ways to Run

Mode 1 — Core Agent (Zero backend required)

Add an LLM key and you're immediately productive:

• ✅ In-place file edits
• ✅ Ask / Plan / Coding modes
• ✅ Checkpoint & rewind
• ✅ Diff review
• ✅ Interactive terminal & file explorer

Mode 2 — Core Agent + Context Engine

Flip on the Context Engine (Settings → Context engine) for graph-aware, repo-scale retrieval powered by:

• tree-sitter → syntax-aware parsing
• Qdrant → vector similarity search
• FalkorDB → call-graph traversal
• BM25 → lexical search

The agent's codebase_search and codebase_graph tools query it automatically. See services/context-engine/README.md.

🛠️ Getting Started

Prebuilt binaries are coming. For now, build from source — it's straightforward.

Prerequisites

• Rust (stable) + Tauri 2 system prerequisites for your OS
• Node.js 20+ and npm
• (Optional, for Context Engine) Docker with Compose

Run the App

cd apps/desktop
npm install

# Development
npm run tauri:dev

# Production build
npm run tauri:build

Windows shortcut: Double-click launch-godcoder.bat in the repo root — it sets up Cargo on PATH and starts the app automatically.

On first launch: Open Settings → add an LLM provider (base_url + api_key + model) → create a session → pick a folder and mode → start coding.

(Optional) Run the Context Engine

cd services/context-engine
cp .env.example .env   # set SUPERCODER_OPENAI_API_KEY (server-side embedding key)
docker compose up -d --build

Then enable Settings → Context engine in the app. Full instructions: services/context-engine/README.md.

🗺️ Roadmap

• Prebuilt releases & installers — CI pipeline for binaries lands next
• Benchmark harness — headless runner over the same agent core, with reproducible per-task sandboxes to measure the harness across models and validate graph-retrieval localization
• Broader provider support — the provider abstraction is built to grow
• Ask / Plan / Coding modes
• Self-optimizing Harness mode (builds its own agent harness)
• Checkpoint & rewind
• MCP server support
• Voice API integration
• Context Engine (local, graph-aware semantic search)

🤝 Contributing

Contributions are welcome! Please read CONTRIBUTING.md to get started.

• 🐛 Found a bug? Open an issue
• 💡 Have an idea? Start a discussion
• ⭐ Like the project? Give it a star — it helps more than you think!

📄 License

MIT © eli-labz