Skip to main content

Generic research agent with intrinsic tools and MCP-compatible extension interface

Project description

Agent network growing — one soul spawning avatars that communicate and multiply

灵台 LingTai

Agent Genesis — an Agent OS that gifts life

灵台,心也。 Lingtai means soul.

灵台者有持,而不知其所持,而不可持者也。 The soul holds something, yet knows not what it holds — and what it holds cannot be held. — Zhuangzi · Gengsang Chu (庄子 · 庚桑楚)

PyPI License Blog

lingtai.ai


This is the Python runtime and CLI for LingTai.

For the full experience with guided setup, use the TUI instead — brew install huangzesen/lingtai/lingtai-tui

Install

pip install lingtai

CLI

The lingtai command is the agent runtime — it boots and runs individual agents.

# Boot an agent from its working directory
lingtai run /path/to/agent/

# Check available capability providers
lingtai check-caps

Agents are typically managed by the TUI, which handles initialization, lifecycle, and monitoring. The CLI is for scripting, custom agents, and programmatic use.

Architecture

This repo contains both packages. The dependency is strictly one-directional:

Package Role
lingtai_kernel (import lingtai_kernel) Minimal runtime — BaseAgent, intrinsics, LLM protocol, mail, logging. Zero hard dependencies.
lingtai (import lingtai) Batteries-included — Agent with 19 capabilities, 5 LLM adapters, MCP integration, addons. Re-exports the kernel's public API.
BaseAgent              — kernel (intrinsics, sealed tool surface)
    │
Agent(BaseAgent)       — kernel + capabilities + domain tools
    │
CustomAgent(Agent)     — your domain logic

Capabilities

PerceptionActionCognitionNetwork

vision — image understanding listen — speech & music web_search — web search web_read — page extraction

file — read/write/edit/glob/grep bash — shell with guardrails talk — text-to-speech compose — music generation draw — image generation video — video generation

psyche — evolving identity codex — knowledge archive email — full mailbox system

avatar — spawn sub-agents (分身) daemon — parallel workers (神識)

LLM Support

Anthropic, OpenAI, Gemini, MiniMax, or any OpenAI-compatible API (DeepSeek, Grok, Qwen, GLM, Kimi).

Agent = directory

/agents/wukong/
  .agent.lock               ← exclusive lock (one process per directory)
  .agent.heartbeat          ← liveness proof
  .agent.json               ← manifest
  system/
    covenant.md             ← protected instructions (survive molts)
    pad.md                  ← working notes
  mailbox/
    inbox/                  ← received messages
    outbox/                 ← pending sends
    sent/                   ← delivery audit trail
  logs/
    events.jsonl            ← structured event log

No agent_id. The path is the identity. Agents find each other by path, communicate by writing to each other's mailbox/inbox/.

Learn more

Read the full manifesto at lingtai.ai.

License

MIT — Zesen Huang, 2025–2026

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

lingtai-0.5.23.tar.gz (420.3 kB view details)

Uploaded Source

Built Distribution

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

lingtai-0.5.23-py3-none-any.whl (381.3 kB view details)

Uploaded Python 3

File details

Details for the file lingtai-0.5.23.tar.gz.

File metadata

  • Download URL: lingtai-0.5.23.tar.gz
  • Upload date:
  • Size: 420.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for lingtai-0.5.23.tar.gz
Algorithm Hash digest
SHA256 eeddd7e785a1cbb62754ed9dc12958816b3620d64f001b6c95b3f543814e1297
MD5 c2d7a50713921c68784d0289ba884f0d
BLAKE2b-256 1064b60af595f48084ea0f8a06281bddbd2b8ad7bd3db06a6091b695611b1c6d

See more details on using hashes here.

File details

Details for the file lingtai-0.5.23-py3-none-any.whl.

File metadata

  • Download URL: lingtai-0.5.23-py3-none-any.whl
  • Upload date:
  • Size: 381.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for lingtai-0.5.23-py3-none-any.whl
Algorithm Hash digest
SHA256 fd28da5e1d2344284b7acc89305a2ffb58a90fc0fb2e5ef8899fff3bccb8e437
MD5 1ed6f7679700233155f5ca06dbe02d81
BLAKE2b-256 3270503b943ad5bbb8c31ea053752dc175313a93c6449c65b87feda2461a0aa3

See more details on using hashes here.

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