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)
lingtai.ai · 简体中文 · 文言 · Contributing · Security · Support
This is the Python runtime and CLI for LingTai.
For the full experience with guided setup, use the TUI instead — brew install lingtai-ai/lingtai/lingtai-tui
pip install lingtaiThe lingtai-agent command is the agent runtime — it boots and runs individual agents.
# Boot an agent from its working directory
lingtai-agent run /path/to/agent/
# Check available capability providers
lingtai-agent check-capsAgents are typically managed by the TUI, which handles initialization, lifecycle, and monitoring. The CLI is for scripting, custom agents, and programmatic use.
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
| Perception | Action | Cognition | Network |
|---|---|---|---|
|
|
|
|
|
Anthropic, OpenAI, Gemini, MiniMax, or any OpenAI-compatible API (DeepSeek, Grok, Qwen, GLM, Kimi).
/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/.
Read the full manifesto at lingtai.ai.
See CONTRIBUTING.md for the contribution workflow and repository navigation entry points. For responsible disclosure, read SECURITY.md; for help, read SUPPORT.md.
See docs/references/acknowledgements.md.
Apache-2.0 — Zesen Huang, 2025–2026
lingtai.ai · GitHub · Contributing · Security · Support · TUI