network-ai 4.5.0 → 4.5.1
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 +7 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
[](https://github.com/jovanSAPFIONEER/Network-AI/actions/workflows/ci.yml)
|
|
6
6
|
[](https://github.com/jovanSAPFIONEER/Network-AI/actions/workflows/codeql.yml)
|
|
7
|
-
[](https://github.com/jovanSAPFIONEER/Network-AI/releases)
|
|
8
8
|
[](https://www.npmjs.com/package/network-ai)
|
|
9
9
|
[](#testing)
|
|
10
10
|
[](#adapter-system)
|
|
@@ -21,6 +21,7 @@ Network-AI is a TypeScript/Node.js multi-agent orchestrator that adds coordinati
|
|
|
21
21
|
- **Shared blackboard with locking** — atomic `propose → validate → commit` prevents race conditions and split-brain failures across parallel agents
|
|
22
22
|
- **Guardrails and budgets** — FSM governance, per-agent token ceilings, HMAC audit trails, and permission gating
|
|
23
23
|
- **14 adapters** — LangChain (+ streaming), AutoGen, CrewAI, OpenAI Assistants, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, Custom (+ streaming), OpenClaw, A2A, and Codex — no glue code, no lock-in
|
|
24
|
+
- **Persistent project memory (Layer 3)** — `context_manager.py` injects decisions, goals, stack, milestones, and banned patterns into every system prompt so agents always have full project context
|
|
24
25
|
|
|
25
26
|
> **The silent failure mode in multi-agent systems:** parallel agents writing to the same key
|
|
26
27
|
> use last-write-wins by default — one agent's result silently overwrites another's mid-flight.
|
|
@@ -56,6 +57,7 @@ Network-AI is a TypeScript/Node.js multi-agent orchestrator that adds coordinati
|
|
|
56
57
|
| No visibility into what agents did | HMAC-signed audit log on every write, permission grant, and FSM transition |
|
|
57
58
|
| Locked into one AI framework | 14 adapters — mix LangChain + AutoGen + CrewAI + Codex + custom in one swarm |
|
|
58
59
|
| Agents escalating beyond their scope | `AuthGuardian` — scoped permission tokens required before sensitive operations |
|
|
60
|
+
| Agents lack project context between runs | `ProjectContextManager` (Layer 3) — inject decisions, goals, stack, and milestones into every system prompt |
|
|
59
61
|
|
|
60
62
|
---
|
|
61
63
|
|
|
@@ -71,10 +73,14 @@ flowchart TD
|
|
|
71
73
|
classDef blackboard fill:#0c4a6e,stroke:#0284c7,color:#bae6fd
|
|
72
74
|
classDef adapters fill:#064e3b,stroke:#059669,color:#a7f3d0
|
|
73
75
|
classDef audit fill:#1e293b,stroke:#475569,color:#94a3b8
|
|
76
|
+
classDef context fill:#3b1f00,stroke:#b45309,color:#fef3c7
|
|
74
77
|
|
|
75
78
|
App["Your Application"]:::app
|
|
76
79
|
App -->|"createSwarmOrchestrator()"| SO
|
|
77
80
|
|
|
81
|
+
PC["ProjectContextManager\n(Layer 3 — persistent memory)\ngoals · stack · decisions\nmilestones · banned"]:::context
|
|
82
|
+
PC -->|"injected into system prompt"| SO
|
|
83
|
+
|
|
78
84
|
subgraph SO["SwarmOrchestrator"]
|
|
79
85
|
AG["AuthGuardian\n(permission gating)"]:::security
|
|
80
86
|
AR["AdapterRegistry\n(route tasks to frameworks)"]:::routing
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "network-ai",
|
|
3
|
-
"version": "4.5.
|
|
3
|
+
"version": "4.5.1",
|
|
4
4
|
"description": "AI agent orchestration framework for TypeScript/Node.js - 14 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw, A2A, Codex + streaming variants). Built-in CLI, security, swarm intelligence, real-time streaming, and agentic workflow patterns.",
|
|
5
5
|
"homepage": "https://github.com/jovanSAPFIONEER/Network-AI#readme",
|
|
6
6
|
"main": "dist/index.js",
|