nervous-system
NERVous System — durable multi-agent orchestration, coding-agent coordination, and workflow recovery for pi.
Package details
Install nervous-system from npm and Pi will load the resources declared by the package manifest.
$ pi install npm:nervous-system- Package
nervous-system- Version
1.0.3- Published
- Jul 11, 2026
- Downloads
- not available
- Author
- 10ego
- License
- MIT
- Types
- extension, skill, prompt
- Size
- 744.1 KB
- Dependencies
- 1 dependency · 5 peers
Pi manifest JSON
{
"extensions": [
"magi/extension/index.ts",
"axon/extension/index.ts",
"synapse/extension/index.ts",
"cortex/extension/index.ts",
"lion/extension/index.ts",
"cerebel/extension/index.ts",
"ganglion/extension/index.ts",
"amygdala/extension/index.ts",
"dashboard/extension/index.ts"
],
"skills": [
"magi/skills/magi",
"axon/skills/axon",
"synapse/skills/synapse",
"cortex/skills/cortex",
"lion/skills/lion",
"cerebel/skills/cerebel",
"ganglion/skills/ganglion",
"amygdala/skills/amygdala"
],
"prompts": [
"magi/prompts",
"cortex/prompts",
"lion/prompts",
"cerebel/prompts",
"ganglion/prompts",
"amygdala/prompts"
],
"image": "https://raw.githubusercontent.com/10ego/NERVous-system/main/assets/nervous-system-gallery.png"
}Security note
Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.
README
NERVous System
A durable multi-agent orchestration and coding-agent coordination framework for pi. NERVous System helps coding agents plan, delegate, coordinate, execute, recover from interruptions, and review work continuously.
You can just give it a task description and walk away.
Find it in the pi package directory by searching for multi-agent orchestration, coding-agent coordination, subagent delegation, durable task planning, workflow recovery, or risk triage.
Quick start
pi install npm:nervous-system
Then start a durable workflow:
/nervous implement this feature with durable planning and worker delegation
NERVous installs the complete suite: CORTEX, MAGI, AXON, SYNAPSE, LION, CEREBEL, GANGLION, AMYGDALA, and the dashboard.
Highlights
- Durable goals and task state that survive compaction, restarts, and interruptions
- Deliberation, risk triage, and explicit verification for difficult work
- Parallel coding subagents with orchestration, capacity allocation, and live progress
- Project- and context-isolated state with a read-only dashboard
Documentation
| Guide | Contents |
|---|---|
| Documentation index | Suggested reading paths and all guides |
| Getting started | Installation, first use, updates, removal, and local development |
| Architecture | Components, execution flow, repository layout, and package design |
| Operations | Worker controls, dashboard, state isolation, and configuration |
| Benchmark | NERVous prompts compared with a raw LLM baseline |
| Release policy | Version compatibility, state policy, and known limitations |
Status: The complete core component set and deterministic end-to-end demo are implemented and tested.
