lcarrere commited on
Commit
c3f5d57
Β·
verified Β·
1 Parent(s): 7efdfeb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +38 -22
README.md CHANGED
@@ -1,54 +1,70 @@
1
  ---
2
  title: README
3
- emoji: πŸ€–
4
  colorFrom: blue
5
  colorTo: purple
6
  sdk: static
7
  pinned: false
8
  ---
9
 
10
- # Local AI Agent Platform for Developers
11
 
12
- **Your AI. Your Data. On Your Device.**
13
 
14
- LM-Kit is a complete platform for building and deploying AI agents with **zero cloud dependency**. It unifies trained models, on-device inference, orchestration, RAG pipelines, MCP-compatible tool calling, and reusable task specialists in a single framework.
15
 
16
- Built for developers who need **complete data sovereignty** and **no external API calls**.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
 
18
  ---
19
 
20
  ## ✨ What You Can Build
21
 
22
- πŸ€– **AI Agents** - Conversational AI with smart memory and MCP tool calling
23
- πŸ“„ **Document Intelligence** - PDF chat, structured extraction, layout analysis
24
- πŸ” **RAG Pipelines** - Semantic search with built-in vector database and Multimodal RAG
25
- πŸ“Š **Analysis Agents** - Sentiment, NER, PII extraction, custom classification
26
- 🌐 **Language Processing** - Translation, speech-to-text, language detection
27
- 🎨 **Vision & Multimodal** - Visual understanding, image embeddings, multimodal search
28
 
29
  ---
30
 
31
- ## πŸš€ Why Local AI?
32
 
33
- - **100% Local Inference** - No data leaves your infrastructure
34
- - **No Per-Token Costs** - Predictable pricing, unlimited inference
35
- - **Cross-Platform** - Windows, macOS, Linux (including ARM64)
36
- - **Offline-Ready** - Works in air-gapped environments
37
- - **Native SDKs** - LM-Kit.NET for .NET developers, with more to come
38
 
39
  ---
40
 
41
  ## πŸ“š Resources
42
 
43
  🌐 **Website:** [lm-kit.com](https://lm-kit.com)
44
- πŸ“– **Documentation:** [docs.lm-kit.com](https://docs.lm-kit.com/lm-kit-net/index.html)
45
  πŸ’» **GitHub Samples:** [LM-Kit Samples](https://github.com/LM-Kit/lm-kit-net-samples)
46
- πŸ“¦ **NuGet:** [LM-Kit.NET Packages](https://www.nuget.org/profiles/LM-Kit)
 
47
 
48
  ---
49
 
50
- ## 🎁 Free Community Edition
51
 
52
- Get started with full SDK access - no signup required, no feature limits.
53
 
54
- πŸ‘‰ [**Download Free**](https://lm-kit.com/products/download/) | [**Community License**](https://lm-kit.com/products/community-edition/)
 
1
  ---
2
  title: README
3
+ emoji: πŸ“„
4
  colorFrom: blue
5
  colorTo: purple
6
  sdk: static
7
  pinned: false
8
  ---
9
 
10
+ # The Private Document Intelligence Platform
11
 
12
+ **From documents to data, knowledge, and action. Privately.**
13
 
14
+ LM-Kit turns documents into structured data, internal knowledge into cited answers, and document workflows into governed automation, entirely on infrastructure you control. No cloud calls, no data leaving your machines, no per-token fees.
15
 
16
+ ---
17
+
18
+ ## 🧩 Two Products, One Engine
19
+
20
+ πŸ–₯️ **[LM-Kit One](https://lm-kit.com/products/lm-kit-one/)** - A private AI server you deploy. Structured extraction, knowledge search with citations, governed document agents and model management, reached over native REST, OpenAI-compatible, Ollama and Anthropic APIs, or from AI assistants over MCP.
21
+
22
+ πŸ“¦ **[LM-Kit.NET](https://lm-kit.com/products/lm-kit-net/)** - The Private Document Intelligence SDK for .NET. The same engine as one NuGet, fully in-process: structured extraction with per-field confidence, OCR, PII redaction, RAG with citations, agents, vision and speech. Zero cloud calls.
23
+
24
+ ---
25
+
26
+ ## πŸ€— Models in This Organization
27
+
28
+ These repositories are the LM-Kit model catalog: curated, quantized builds maintained for both products.
29
+
30
+ - **`*-gguf`** - Standard GGUF quantizations, usable with any GGUF-compatible runtime
31
+ - **`*-lmk`** - The same models packaged in the LM-Kit format, loaded directly by model ID, for example `LM.LoadFromModelID("qwen3.8:27b")`
32
 
33
  ---
34
 
35
  ## ✨ What You Can Build
36
 
37
+ πŸ“„ **Documents to data** - Schema-driven extraction with per-field confidence, OCR, layout analysis, Markdown conversion
38
+ πŸ” **Knowledge with citations** - Hybrid search and RAG over internal documents, with answers citing document and page
39
+ πŸ›‘οΈ **Privacy workflows** - PII detection, redaction, classification, named entity recognition
40
+ πŸ€– **Governed agents** - Tool calling under permission policies, memory, MCP
41
+ 🎨 **Vision** - Visual document understanding, image embeddings, multimodal search
42
+ πŸŽ™οΈ **Speech** - Local speech-to-text and transcription
43
 
44
  ---
45
 
46
+ ## πŸ”’ Why Private?
47
 
48
+ - **Private by architecture** - Inference runs on your hardware; offline and air-gapped deployments work
49
+ - **Verifiable by output** - Extractions carry confidence scores, answers carry citations
50
+ - **Governed in operation** - Permission policies decide what agents and tools may do
51
+ - **Cross-platform** - Windows, Linux, macOS (including ARM64)
52
+ - **No per-token fees** - Predictable licensing, unlimited inference
53
 
54
  ---
55
 
56
  ## πŸ“š Resources
57
 
58
  🌐 **Website:** [lm-kit.com](https://lm-kit.com)
59
+ πŸ“– **Documentation:** [docs.lm-kit.com](https://docs.lm-kit.com/)
60
  πŸ’» **GitHub Samples:** [LM-Kit Samples](https://github.com/LM-Kit/lm-kit-net-samples)
61
+ πŸ“¦ **NuGet:** [LM-Kit.NET Packages](https://www.nuget.org/profiles/LM-Kit)
62
+ πŸ›‘οΈ **Trust Center:** [lm-kit.com/trust](https://lm-kit.com/trust/)
63
 
64
  ---
65
 
66
+ ## 🎁 Free for Small Businesses and Education
67
 
68
+ Our mission is to empower every organization with private AI. Both products are free for small businesses and for education, including commercial use, with nothing to activate and no runtime license check. Evaluation and development are free at any company size.
69
 
70
+ πŸ‘‰ [**Free Download**](https://lm-kit.com/products/download/) | [**LM-Kit One**](https://lm-kit.com/products/lm-kit-one/) | [**Pricing**](https://lm-kit.com/pricing/)