A local-first, open-source AI coding agent that runs as a native desktop app, letting you bring your own LLM key while keeping code on your machine.

Stars

238

7-day growth

No data

Forks

8

Open issues

0

License

NOASSERTION

Last updated

2026-07-04

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It introduces a real-time self-optimizing harness mode where the agent writes and improves its own agent tools and workflow, plus a CoWork mode for GUI/OS automation—all without data leaving your machine.

Who it is for

  • Developers who require code privacy and prefer local execution
  • Engineers automating repetitive coding or refactoring tasks
  • Researchers exploring self-improving AI agent loops
  • Users needing desktop automation beyond code editing

Use cases

  • Autonomously improving a codebase by running Harness mode to build and refine agent tools
  • Automating human‑action tasks (clicking, typing, sending email) through CoWork mode
  • Navigating large codebases with graph-aware semantic search via the Context Engine
  • Iterative coding with checkpoints, diff review, and multi‑mode sessions

Strengths

  • Fully local‑first—no vendor backend, no data transit; code stays on your machine
  • Real‑time self‑building harness that compounds knowledge over iterations
  • Supports any OpenAI‑compatible LLM provider, MCP servers, and voice APIs
  • Open‑source (MIT) with a clear modular architecture (Rust core + Tauri desktop)

Considerations

  • No prebuilt binaries yet; must build from source (requires Rust, Node.js, and Tauri prerequisites)
  • Requires the user to supply their own LLM API key and model endpoint
  • CoWork mode depends on the third‑party Open Cowork desktop app for GUI/OS actuation

README quick start

⚡ Godcoder

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

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

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.

It goes beyond editing code: Godcoder can build and continuously improve its own agent harness (Harness mode) and self-train to drive the Open Cowork desktop app, even executing human-action tasks — clicking, typing, opening apps, sending email, e-signing — through GUI/OS automation (CoWork mode). Both modes run a self-optimizing loop that compounds lessons over time, so the agent gets measurably better with use.

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                                                      │
│    │                                                        │
│    ▼                                                        │

Description

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.

Related repositories

Similar projects matched by category, topics, and programming language.

l0ng-ai
Featured
l0ng-ai GitHub avatar

tty7

tty7 is a fast, GPU-accelerated terminal workbench with persistent sessions, built-in input tools, SSH support, and coding agent awareness.

Developer ToolsCLI & Terminal
359
steelbrain
Featured
steelbrain GitHub avatar

reims-vgpu

reims-vgpu is an experimental virtual GPU for macOS guests that uses QEMU to decode the guest's GPU command stream and execute it through Metal or Vulkan, leveraging the built-in AppleParavirtGPU driver without requiring custom kexts.

Desktop Apps
143
m-novotny
Featured
m-novotny GitHub avatar

memguard-rs

A Rust library that provides secure memory handling primitives including zeroization on drop, memory locking, constant-time comparison, and compile-time guarded regions, with zero dependencies and no_std support.

Embedded & IoTSecurity
131