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-0.3.7.tar.gz (3.4 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-0.3.7-py3-none-any.whl (3.8 kB view details)

Uploaded Python 3

File details

Details for the file genesis_ai-0.3.7.tar.gz.

File metadata

  • Download URL: genesis_ai-0.3.7.tar.gz
  • Upload date:
  • Size: 3.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for genesis_ai-0.3.7.tar.gz
Algorithm Hash digest
SHA256 beae3a4ca71ec7bb7f3bf05b4b8d5bc78a596a9b767f6bd64020d4c3effcc91b
MD5 8341edfc5178f1495bbb04547d3f848a
BLAKE2b-256 9474711fd18aef77091daa8243442b7284fe44448ba18041042a9b01858e8cf4

See more details on using hashes here.

Provenance

The following attestation bundles were made for genesis_ai-0.3.7.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-0.3.7-py3-none-any.whl.

File metadata

  • Download URL: genesis_ai-0.3.7-py3-none-any.whl
  • Upload date:
  • Size: 3.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for genesis_ai-0.3.7-py3-none-any.whl
Algorithm Hash digest
SHA256 8d230c296d2c8279942081a1e41d2429632e934d3535544c9e43b7a973b3a56e
MD5 d42b173138dcc374f126b70eb3439c66
BLAKE2b-256 898d7cb31324165e54c5fd7f9013af81bced6f1d196096e76d7ea8ec77467c81

See more details on using hashes here.

Provenance

The following attestation bundles were made for genesis_ai-0.3.7-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