Skip to main content

Genesis — universal autonomous AI agent with multi-agent swarm execution

Project description

Genesis

Genesis

Universal autonomous AI agent built in Zig

Genesis runs in the terminal, in the browser, and inside messaging platforms — with multi-agent swarm execution when a single agent isn't enough.

Install

pip install genesis-ai

Usage

genesis                                                # interactive TUI
genesis --provider anthropic --model claude-sonnet-4-6  # specific provider
genesis --task "Build a REST API"                      # swarm mode
genesis --server --transport ws --listen 0.0.0.0:7700  # server mode

Highlights

  • Interactive TUI — streaming chat, markdown rendering, 6 themes (dark/light)
  • Web UI — browser interface with artifact viewer, file browser, inline downloads
  • VS Code extension — full-featured sidebar with chat, voice input, file attachments
  • Channel adapters — Telegram, Discord, Slack, X; custom channels via JSON-RPC stdio
  • Vision fallback — automatic image/video analysis for non-vision models
  • Voice input — speech-to-text via /voice command
  • Multi-provider — Anthropic, z.ai, OpenAI, Google, OpenRouter, Chutes, Moonshot, MiniMax
  • Swarm engine — parallel multi-agent execution with role differentiation
  • Subagents — lightweight parallel tasks with workspace isolation
  • MCP support — external tools through Model Context Protocol
  • Built-in tools — file editing, shell, glob, web search/fetch, scheduler, vault
  • Permission system — safe/normal/auto/yolo modes

Documentation

Full documentation: github.com/deadraid/genesis

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

genesis_ai-0.5.0.tar.gz (3.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

genesis_ai-0.5.0-py3-none-any.whl (3.9 kB view details)

Uploaded Python 3

File details

Details for the file genesis_ai-0.5.0.tar.gz.

File metadata

  • Download URL: genesis_ai-0.5.0.tar.gz
  • Upload date:
  • Size: 3.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for genesis_ai-0.5.0.tar.gz
Algorithm Hash digest
SHA256 760d952f7193c705aca400acd953e17bd04728602dfc62c4f9d4e11d83139720
MD5 4d3828969fe763f94fca12293312adff
BLAKE2b-256 10e8b874952929108abf76b06829c3be1143b041d96989a3e6503f8728008a46

See more details on using hashes here.

Provenance

The following attestation bundles were made for genesis_ai-0.5.0.tar.gz:

Publisher: release.yml on deadraid/genesis

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file genesis_ai-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: genesis_ai-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 3.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for genesis_ai-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2c350fbf5a88337b25dff954aca11cc87c68b781c9f3aa3fa983272ffa17b7ca
MD5 704f993f4f33210c7c64f3fc86ee5160
BLAKE2b-256 648bea7ecd21a7787949a8b81d2c7885cd248cef300cb539e00a2a00ffc27e27

See more details on using hashes here.

Provenance

The following attestation bundles were made for genesis_ai-0.5.0-py3-none-any.whl:

Publisher: release.yml on deadraid/genesis

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page