Skip to content

eli-labz/Godcoder

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

⚡ Godcoder

A local-first, open-source AI coding agent for your desktop.

Bring your own LLM key. Your code never leaves your machine.

License: MIT Built with Rust Tauri 2 Stars Forks

Download · Features · Architecture · Contribute


🚀 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.


🧬 The Agent Builds Its Own Harness — Live

Godcoder doesn't just use a harness. It writes one, improves it, and optimizes it — autonomously, in real time.

This is the defining capability that sets Godcoder apart. Activate Harness mode and the agent takes over its own agent loop: it scaffolds a live sandbox, engineers its own tools and workflows, runs improvement cycles, measures what works, and compounds that knowledge — all without you writing a single prompt.

┌─────────────────────────────────────────────────────────────┐
│              HARNESS MODE  —  Real-Time Self-Build          │
│                                                             │
│  START                                                      │
│    │                                                        │
│    ▼                                                        │
│  🏗️  Scaffold  →  creates harness-build/ sandbox            │
│    │                                                        │
│    ▼                                                        │
│  🗺️  Route     →  selects the highest-value next change     │
│    │                                                        │
│    ▼                                                        │
│  📋  Plan      →  designs the improvement                   │
│    │                                                        │
│    ▼                                                        │
│  ⚙️  Execute   →  writes, edits, runs code                  │
│    │                                                        │
│    ▼                                                        │
│  ✅  Evaluate  →  verifies with the project's own checks    │
│    │                                                        │
│    ▼                                                        │
│  📝  Log       →  records outcome in persistent memory      │
│    │                                                        │
│    ▼                                                        │
│  🔁  Optimize  →  biases future iterations toward success   │
│    │                                                        │
│    └──────────────────────────────► repeat                  │
└─────────────────────────────────────────────────────────────┘

How it works:

  • Pick Harness in the new-session composer and press start — no prompt to type, no folder to choose.
  • The agent instantly creates a dedicated harness-build/ workspace, opens it in your file explorer, and confines all new work there — reading the rest of the repo for reference but never rewriting it.
  • Each iteration makes one decisive, verifiable change: keep it if it's an improvement, discard it otherwise.
  • Results are stored in a persistent memory store (via the ResearchSwarm bridge) so lessons from past runs rank and steer future iterations — the harness compounds knowledge over time.
  • Like Freestyle mode, every tool call is auto-approved after the first confirmation.

The loop is powered by the self-optimizing-harness default skill and a ResearchSwarm bridge exposing route / log / recall / optimize over a persistent memory store.


✨ What Godcoder Can Do

Feature Description
🧬 Real-Time Self-Built Harness The agent scaffolds, writes, and optimizes its own agent harness live — no human prompting required
🧠 Ask / Plan / Coding / Freestyle / Harness Modes From answering questions to fully autonomous coding — pick the depth that fits your task
📝 In-place File Editing Edit files, review diffs, rewind to checkpoints, continue from previous turns
🖥️ Interactive Terminal Built-in terminal, file explorer, and session history
🔌 Any LLM Provider Plug in OpenAI, Anthropic, or any OpenAI-compatible endpoint — no proxy needed
🛠️ MCP Server Support Extend the toolset with MCP servers over stdio, streamable HTTP, or SSE
🎙️ Voice API Integration Configure TTS, STT, and Voice-to-Voice from Settings — stored locally
🔍 Graph-Aware Code Search Optional Context Engine: semantic + structural search over large codebases
🔒 Tool Approval Controls Deliberate execution with subagents, skills, and approval gates

🏗️ 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

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 — agent builds and improves its own harness in real time
  • 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.


📄 License

MIT © eli-labz

If Godcoder saves you time, please consider giving it a ⭐ — it helps the project grow!

About

A local-first, open-source coding agent for your desktop. Bring your own LLM key; your code stays on your machine and only ever leaves to the model provider. The AI Agent builds its own Harnes.

Topics

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Packages

 
 
 

Contributors