Star 历史趋势
数据来源: GitHub API · 生成自 Stargazers.cn
README.md

EvoX Genesis

One objective in. A software world unfolds.

Open-source AI agents for software development.
Describe the software you want. Genesis coordinates agents to build, validate, and evolve it.

Download Genesis · Website · Docs · Evidence · Paper

https://github.com/user-attachments/assets/d7f3d520-e39f-45cd-a525-77e5e8d00a75

Eighty seconds. One objective.
Watch the film on the website →

See development unfold

  • Set an objective. Start a new project or bring an existing repository. Describe the outcome and constraints; Genesis decomposes the work as needed.
  • Follow the work. Watch the recursive agent tree, inspect tasks and model usage, and review diffs in the desktop dashboard.
  • Keep developing. Continue from accepted results, refine the objective, or move execution to a server while keeping your local dashboard.

New projects · Existing repositories · Remote development

Built with Genesis

Selected software worlds developed with Genesis.

ProjectWhat emergedReported result
C CompilerA Rust-based C compiler built from scratch220 / 220 c-testsuite
MESA13 Fortran modules redeveloped in Rust1,052 / 1,052 (0 failures) Rust test suite
tbench-wasmA software WebGL renderer in TypeScript2,017 / 2,019 (99.90%) Khronos WebGL CTS

Latest evidence: EvoX Compiler · 2026-10-28

Explore all evidence →

The world persists. Agents do not.

Managers delegate work to executors. Accepted contributions persist in version history after agent episodes end.

An objective becomes local work. Managers break down the goal, delegate tasks, and review the results. Executors implement and validate candidate changes in isolated Git worktrees.

Each task has a place. An accepted software version records what has been built; a repository path defines context, responsibility, and scope. CONTEXT.md files make these local contracts explicit.

Accepted results carry forward. The hierarchy unfolds as development proceeds. Agents finish their episodes; software versions and project history remain as the starting point for subsequent work.

Explore the architecture →


Start with an objective

Desktop app

Download Genesis → for macOS, Linux, or Windows. The website selects the installer for your platform; all published builds are available in GitHub Releases.

  1. Install and open Genesis.
  2. Choose a model provider and model, and configure your API credentials.
  3. Create a project or select an existing repository, then describe what you want to build.

For example:

Add rate limiting to this API. Preserve existing endpoint behavior, make the limits configurable, and add tests for requests above and below the limit.

Installation guide · Model configuration

Want to understand or operate Genesis? Open Assistant (/help) — Genesis Assistant understands the running system and can act on it: it reads Genesis source and inspects runtime state without approval, drives tasks and scheduler/configuration changes only after you approve the exact action, and answers in your language. See the Genesis Assistant guide for capabilities and safety boundaries.

Headless server

Run the dashboard and agent runtime on Linux (x86_64 or ARM64) or macOS (Apple Silicon):

curl -LsSf https://genesis.evox.group/dl/install.sh | sh
genesis start
genesis status

Open http://127.0.0.1:9999 and configure your model provider in Settings. The server listens on localhost by default and has no built-in authentication; use an SSH tunnel for remote access.

Server installation and service management →

Remote development

Keep the desktop dashboard on your laptop and run agents on a server through an encrypted SSH tunnel. Tasks continue when the connection drops, and you can manage multiple remote targets from one dashboard.

Set up remote development →

Built for long-running development

Three layers: the Tauri desktop shell supervises the backend; the Phoenix LiveView dashboard exposes tasks, agents and diffs; the Elixir/OTP core schedules agents and manages Git worktrees.

Git records software versions; SQLite stores runtime and task data. Candidate changes run in isolated worktrees, with platform-specific execution controls described in the sandbox documentation.

Run from source

Use Elixir 1.20.4 and Erlang/OTP 29 to match the repository's CI environment, with Git installed.

git clone https://github.com/EMI-Group/genesis.git
cd genesis
mix deps.get
mix assets.setup
mix phx.server

Open http://localhost:4100.

Build the desktop app or use the Nix dev shell →

Benchmark your machine's I/O

Agents create worktrees, read and write files, and commit changes. Measure this workload on your filesystem:

mix bench.io
mix bench.io --dir /mnt/nvme --iterations 10 --files 500 --writes 50
mix bench.io --json > bench.json

The benchmark creates and removes its own throwaway repository without starting the Genesis runtime. Results cover worktree creation, reads and writes, Git operations, and worktree reclamation.

Research, community, and contributions

Genesis is developed by the EvoX Group at The Hong Kong Polytechnic University. For research and collaboration, get in touch. For bugs and feature requests, open an issue.

Contributions are welcome. See CONTRIBUTING.md for development guidelines and the contributor license agreement, which the CLA assistant handles on your first pull request.

Genesis grew out of EvoGit and follows the broader EvoX research lineage.

Released under the GNU Affero General Public License v3.0.

关于 About

EvoX Genesis is an autonomous system for long-horizon software evolution that recursively builds, continues, and transforms complex software from high-level objectives.
agentic-aiagentic-codingagentic-frameworkagentic-osautonomous-agentsautonomous-codingautonomous-software-developmentevoxlong-horizon-agentslong-horizon-ailong-horizon-governancelong-horizon-intelligencelong-horizon-planninglong-horizon-taskslong-term-memoryvibecoding

语言 Languages

Elixir94.9%
Rust1.5%
Shell1.1%
JavaScript0.8%
CSS0.7%
HTML0.7%
Nix0.2%
Python0.1%
Dockerfile0.0%

提交活跃度 Commit Activity

代码提交热力图
过去 52 周的开发活跃度
9271
Total Commits
峰值: 801次/周
Less
More

核心贡献者 Contributors