@nxuss/lemma 0.5.0 → 0.5.1
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 +61 -8
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -1,5 +1,20 @@
|
|
|
1
|
-
# Lemma v0.5.0
|
|
2
|
-
|
|
1
|
+
# 🧠 Lemma v0.5.0
|
|
2
|
+
|
|
3
|
+
[](https://www.npmjs.com/package/@nxuss/lemma)
|
|
4
|
+
[](https://github.com/Nxusbets/lemma/blob/main/LICENSE)
|
|
5
|
+
[]()
|
|
6
|
+
[]()
|
|
7
|
+
[]()
|
|
8
|
+
|
|
9
|
+
```text
|
|
10
|
+
__
|
|
11
|
+
/ / ___ ____ ___ ____ ___ ____ _
|
|
12
|
+
/ / / _ \/ __ `__ \/ __ `__ \/ __ `/
|
|
13
|
+
/ /___/ __/ / / / / / / / / / / /_/ /
|
|
14
|
+
/_____/\___/_/ /_/ /_/_/ /_/ /_/\__,_/
|
|
15
|
+
|
|
16
|
+
```
|
|
17
|
+
> **The Intelligent local-first AI Gateway — Privacy, Performance, and Precision for the Agentic Era.**
|
|
3
18
|
|
|
4
19
|
Lemma is a high-performance orchestration layer that sits between your development environment and LLM providers. It transforms the way you build with AI by providing **Shared Semantic Memory**, **Autonomous Cost Optimization**, and **Privacy Guardrails**.
|
|
5
20
|
|
|
@@ -7,6 +22,9 @@ Lemma is a high-performance orchestration layer that sits between your developme
|
|
|
7
22
|
|
|
8
23
|
## ⚡ Killer Features
|
|
9
24
|
|
|
25
|
+
### 🖥️ Real-Time Telemetry & Time-Travel Dashboard
|
|
26
|
+
**Full Observability & Interactive Debugging.** Spin up a gorgeous React-based dashboard at `http://localhost:8081/dashboard/` to monitor your entire AI workflow. View real-time charts of cost savings, token compactions, and cache hits. Walk through complex multi-agent conversations step-by-step using a time-travel slider, select and inspect active agent states, and export detailed telemetry audits instantly.
|
|
27
|
+
|
|
10
28
|
### ✂️ Codebase Context Squeezer & Incremental Diff Engine
|
|
11
29
|
**Massive Speedups & Zero Token Waste.** Get instant model responses and make your context windows go up to 10x further. Lemma dynamically optimizes outgoing codebase payloads to prevent redundant data from cluttering your chat, letting you enjoy incredibly long chat histories and ultra-fast generation speeds in Cursor, VS Code, and other IDEs without changing your workflow. Save up to 95% on token consumption automatically.
|
|
12
30
|
|
|
@@ -33,23 +51,56 @@ Lemma is a high-performance orchestration layer that sits between your developme
|
|
|
33
51
|
|
|
34
52
|
---
|
|
35
53
|
|
|
54
|
+
## 🔌 Native SDKs: LangChain & CrewAI Integration
|
|
55
|
+
|
|
56
|
+
Lemma isn't just for IDE chats. Bring enterprise privacy and cost-savings to your codebases and agentic frameworks.
|
|
57
|
+
|
|
58
|
+
### 🦜 LangChain Integration
|
|
59
|
+
Run secure, ultra-efficient chains with a single line of code. Lemma integrates natively as a first-class provider in LangChain, tree-shaking outgoing tool calls and caching complex semantic queries.
|
|
60
|
+
```typescript
|
|
61
|
+
import { LemmaLangChainProvider } from '@nxuss/lemma/langchain';
|
|
62
|
+
|
|
63
|
+
const model = new LemmaLangChainProvider({
|
|
64
|
+
apiKey: process.env.OPENAI_API_KEY,
|
|
65
|
+
});
|
|
66
|
+
```
|
|
67
|
+
|
|
68
|
+
### 👥 CrewAI Integration
|
|
69
|
+
Coordinate heavy multi-agent swarms without breaking your bank. Lemma automatically handles agent-to-agent communication compression, prevents token bloat, and provides high-speed consensus caching.
|
|
70
|
+
```typescript
|
|
71
|
+
import { LemmaCrewAIProvider } from '@nxuss/lemma/crewai';
|
|
72
|
+
|
|
73
|
+
const crew = new LemmaCrewAIProvider({
|
|
74
|
+
agents: [...],
|
|
75
|
+
});
|
|
76
|
+
```
|
|
77
|
+
|
|
78
|
+
---
|
|
79
|
+
|
|
36
80
|
## 🚀 Smart CLI (Zero-Config)
|
|
37
81
|
|
|
38
|
-
Lemma
|
|
82
|
+
Lemma introduces a powerful, unified command-line tool. Get started, monitor, and manage your local AI gateway effortlessly:
|
|
39
83
|
|
|
40
84
|
```bash
|
|
41
|
-
# 1. Install
|
|
85
|
+
# 1. Install globally
|
|
42
86
|
npm install -g @nxuss/lemma
|
|
43
87
|
|
|
44
|
-
# 2. Initialize (Auto-configures
|
|
88
|
+
# 2. Initialize (Auto-configures local database and environment)
|
|
45
89
|
lemma init
|
|
46
90
|
|
|
47
|
-
# 3.
|
|
91
|
+
# 3. Spin up the gateway and launch the gorgeous dashboard
|
|
48
92
|
lemma start
|
|
49
93
|
```
|
|
50
94
|
|
|
51
|
-
###
|
|
52
|
-
|
|
95
|
+
### 🛠️ CLI Reference
|
|
96
|
+
|
|
97
|
+
| Command | Action |
|
|
98
|
+
| :--- | :--- |
|
|
99
|
+
| `lemma init` | Bootstraps configuration files and local cache environments. |
|
|
100
|
+
| `lemma start` | Launches the server, starts local models, and opens the React telemetry UI. |
|
|
101
|
+
| `lemma stop` | Gracefully shuts down the background proxy and databases. |
|
|
102
|
+
| `lemma status` | Displays active optimization modules, system health, and open connections. |
|
|
103
|
+
| `lemma stats` | Outputs high-density metrics showing your real-time token and financial savings. |
|
|
53
104
|
|
|
54
105
|
---
|
|
55
106
|
|
|
@@ -62,6 +113,7 @@ On startup, Lemma performs a **System Check** to detect dependencies like Ollama
|
|
|
62
113
|
| **Caching** | Exact Match | **Semantic Memory** |
|
|
63
114
|
| **Hive Mind** | Local Only | **Cloud Sync (Team Memory)** |
|
|
64
115
|
| **Telepathy** | Basic Sync | **Advanced State Injection** |
|
|
116
|
+
| **Telemetry Dashboard** | Basic Stats | **Time-Travel Debugger & 60fps Graph** |
|
|
65
117
|
| **Limits** | 300 requests/mo | **Unlimited Agentic Power** |
|
|
66
118
|
|
|
67
119
|
---
|
|
@@ -106,6 +158,7 @@ Add the following to your `claude_desktop_config.json` configuration file:
|
|
|
106
158
|
1. **Privacy:** Your IDE won't leak your secrets to the cloud.
|
|
107
159
|
2. **Context:** Lemma syncs your runtime crashes directly to your chat window.
|
|
108
160
|
3. **Speed:** Instant responses for similar questions via Semantic Cache.
|
|
161
|
+
4. **Observability:** Gorgeous dashboard showing you exactly how much cash and tokens you are saving.
|
|
109
162
|
|
|
110
163
|
---
|
|
111
164
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@nxuss/lemma",
|
|
3
|
-
"version": "0.5.
|
|
3
|
+
"version": "0.5.1",
|
|
4
4
|
"description": "Intelligent AI Gateway for IDEs & Agents — Semantic cache, Privacy Firewall, and Autonomous Cost-Optimization.",
|
|
5
5
|
"main": "./dist/cjs/index.js",
|
|
6
6
|
"module": "./dist/esm/index.js",
|
|
@@ -162,7 +162,7 @@
|
|
|
162
162
|
"dependencies": {
|
|
163
163
|
"@chroma-core/default-embed": "^0.1.9",
|
|
164
164
|
"@modelcontextprotocol/sdk": "^1.29.0",
|
|
165
|
-
"@nxuss/lemma": "^0.5.
|
|
165
|
+
"@nxuss/lemma": "^0.5.1",
|
|
166
166
|
"@types/cors": "^2.8.19",
|
|
167
167
|
"axios": "^1.6.0",
|
|
168
168
|
"commander": "^14.0.3",
|