@neuroverseos/governance 0.1.2 → 0.1.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +35 -6
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -1,8 +1,15 @@
|
|
|
1
|
-
# NeuroVerse Governance
|
|
1
|
+
# NeuroVerse Governance — Deterministic Governance Engine for AI Agents
|
|
2
2
|
|
|
3
3
|
**Define governance rules once and enforce them anywhere AI or automated systems operate.**
|
|
4
4
|
|
|
5
|
-
NeuroVerse
|
|
5
|
+
NeuroVerse Governance is a deterministic AI governance engine and policy engine for AI agents. It lets developers enforce AI guardrails, compliance rules, and safety policies on AI systems — with full audit trails and portable, world-based policy definitions. Use it as an agent governance layer for LangChain, OpenAI, or any AI framework.
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
npm install @neuroverseos/governance
|
|
9
|
+
npx neuroverse init
|
|
10
|
+
echo '{"intent":"delete_user","tool":"database"}' | npx neuroverse guard --world .neuroverse/worlds/governance_policy
|
|
11
|
+
# → BLOCK: destructive database operation requires approval
|
|
12
|
+
```
|
|
6
13
|
|
|
7
14
|
## The 10-Second Mental Model
|
|
8
15
|
|
|
@@ -28,16 +35,16 @@ World files are not locked to NeuroVerse. They are **portable rule systems** —
|
|
|
28
35
|
## Install
|
|
29
36
|
|
|
30
37
|
```bash
|
|
31
|
-
npm install
|
|
38
|
+
npm install @neuroverseos/governance
|
|
32
39
|
```
|
|
33
40
|
|
|
34
41
|
## Quick Start
|
|
35
42
|
|
|
36
43
|
```bash
|
|
37
|
-
npm install
|
|
44
|
+
npm install @neuroverseos/governance
|
|
38
45
|
npx neuroverse init
|
|
39
|
-
neuroverse build governance-policy.md
|
|
40
|
-
neuroverse guard --world .neuroverse/worlds/governance_policy
|
|
46
|
+
npx neuroverse build governance-policy.md
|
|
47
|
+
npx neuroverse guard --world .neuroverse/worlds/governance_policy
|
|
41
48
|
```
|
|
42
49
|
|
|
43
50
|
Or explore what's available:
|
|
@@ -46,6 +53,28 @@ Or explore what's available:
|
|
|
46
53
|
npx neuroverse --help
|
|
47
54
|
```
|
|
48
55
|
|
|
56
|
+
## Build a World from Your Documents
|
|
57
|
+
|
|
58
|
+
Already have notes, policies, or design docs? NeuroVerse can turn them into a governance world automatically.
|
|
59
|
+
|
|
60
|
+
```
|
|
61
|
+
my-policies/
|
|
62
|
+
safety-rules.md
|
|
63
|
+
api-restrictions.md
|
|
64
|
+
compliance-notes.md
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
```bash
|
|
68
|
+
npx neuroverse derive --input ./my-policies/ --output safety-world.nv-world.md
|
|
69
|
+
npx neuroverse build safety-world.nv-world.md
|
|
70
|
+
npx neuroverse simulate safety-world --steps 5
|
|
71
|
+
npx neuroverse guard --world .neuroverse/worlds/safety_world
|
|
72
|
+
```
|
|
73
|
+
|
|
74
|
+
That's the full loop: **documents → world → simulation → enforcement**.
|
|
75
|
+
|
|
76
|
+
You don't need to write structured rules by hand — `derive` reads your markdown and synthesizes them into a world definition that `build` can compile.
|
|
77
|
+
|
|
49
78
|
## Quick Example: AI Safety Governance
|
|
50
79
|
|
|
51
80
|
Define rules that restrict unsafe agent behavior, then enforce them at runtime.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@neuroverseos/governance",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.3",
|
|
4
4
|
"description": "Deterministic governance engine for AI agents — evaluate events against world definitions with full audit trace",
|
|
5
5
|
"license": "Apache-2.0",
|
|
6
6
|
"type": "module",
|
|
@@ -75,7 +75,7 @@
|
|
|
75
75
|
],
|
|
76
76
|
"repository": {
|
|
77
77
|
"type": "git",
|
|
78
|
-
"url": "
|
|
78
|
+
"url": "https://github.com/neuroverseos/neuroverseos-governance.git"
|
|
79
79
|
},
|
|
80
80
|
"engines": {
|
|
81
81
|
"node": ">=18"
|