nchhaya commited on
Commit
bd81c57
·
verified ·
1 Parent(s): c1721e4

Add Get started section, POC CTA, tutorial link, UTM tracking on Hyperbots links

Browse files
Files changed (1) hide show
  1. README.md +18 -7
README.md CHANGED
@@ -2,7 +2,7 @@
2
  title: Hyperbots
3
  logo: https://www.hyperbots.com/wp-content/uploads/2023/12/hyperbots-logo.png
4
  github: hyperbots-ai
5
- website: https://www.hyperbots.com
6
  type: company
7
  location: New York, NY & Bengaluru, India
8
  ---
@@ -12,9 +12,10 @@ location: New York, NY & Bengaluru, India
12
 
13
  <p>
14
  <a href="https://huggingface.co/spaces/nchhaya/hyperapi-demo"><b>▶️ Live demo</b></a> ·
15
- <a href="https://apis.hyperbots.com/dashboard/register"><b>🔑 Get a free API key</b></a> ·
16
- <a href="https://apis.hyperbots.com/sandbox"><b>🧪 Try the sandbox</b></a> ·
17
- <a href="https://apis.hyperbots.com/docs"><b>📚 Docs</b></a> ·
 
18
  <a href="https://huggingface.co/spaces/hyperbots-inc/HyperAPI"><b>🧾 HyperAPI Space</b></a> ·
19
  <a href="https://huggingface.co/collections/hyperbots-inc/hyperapi-enterprise-document-intelligence-6af6c8764547d894d4e1a3c4"><b>🗂 Collection</b></a>
20
  </p>
@@ -35,7 +36,7 @@ location: New York, NY & Bengaluru, India
35
 
36
  Every response includes per-field confidence, source boxes, document-level checks (for example, line items must add up to the total), and `request_id`, `model_used`, duration and page count for audit. You can run calls sync, async (`X-Async`) or through the Batch API with webhooks. Results are cached for 24 hours, and cached re-runs are not billed.
37
 
38
- [Get a free key](https://apis.hyperbots.com/dashboard/register) (30 pages/month, no credit card), set `HYPERAPI_KEY` and follow the [quickstart](https://apis.hyperbots.com/docs/quickstart) to use the SDK or REST API:
39
 
40
  ```python
41
  from hyperapi import HyperAPIClient
@@ -83,19 +84,29 @@ HyperAPI's five operations can be exposed to agents over **MCP** (available on r
83
 
84
  ## The models
85
 
86
- HyperAPI runs on **HyperLM**, Hyperbots' mixture-of-experts document stack. It combines small, vision and large language models with multimodal encoders for layout, text and image, and decoders specialised by task and field. HyperLM is trained on **35M+ real-world documents and 0.5B synthetic samples** and retrained continuously. Related research: [**DocuLite**](https://www.hyperbots.com/research/breaking-the-annotation-barrier-with-doculite) (4th Deployable AI Workshop, AAAI 2026) shows how to adapt small LLMs and VLMs to invoice extraction with synthetic data instead of human annotation.
87
 
88
  ## Security and enterprise deployment
89
 
90
  ISO 27001, SOC 1 Type 2 and SOC 2 Type 2. Documents are processed in memory and deleted when the run completes unless you enable retention, and customer data is never used for training. Redaction can run before a document reaches any model. BYOK, IP allow-listing, SSO (Okta, Entra ID, Google Workspace, OneLogin), role-based access and full audit trails are available. Enterprise evaluations run as a POC on your own sample documents, scored field by field against an answer key.
91
 
 
 
 
 
 
 
 
 
 
92
  ## 📰 Read more
93
 
94
  - [Introducing HyperAPI: one API for every enterprise document, plus ten open benchmarks](https://huggingface.co/blog/nchhaya/introducing-hyperapi)
 
95
  - [Live demo Space](https://huggingface.co/spaces/nchhaya/hyperapi-demo): try classify, parse, extract, redact and split on synthetic examples or your own test file
96
 
97
  ## About Hyperbots
98
 
99
  Hyperbots builds AI agents for finance and accounting (procure-to-pay, order-to-cash and the CFO office). HyperAPI is the same document intelligence that runs inside those agents, offered as APIs. The team has 150+ people, including 50 machine-learning scientists, with 50+ patents and 100+ publications.
100
 
101
- [apis.hyperbots.com](https://apis.hyperbots.com) · [hyperbots.com](https://www.hyperbots.com) · [GitHub SDK](https://github.com/hyprbots/hyperapi-sdk) · [LinkedIn](https://www.linkedin.com/company/hyperbots-inc) · [X](https://x.com/hyprbots) · [hyperapi-support@hyperbots.com](mailto:hyperapi-support@hyperbots.com) · [research@hyperbots.com](mailto:research@hyperbots.com)
 
2
  title: Hyperbots
3
  logo: https://www.hyperbots.com/wp-content/uploads/2023/12/hyperbots-logo.png
4
  github: hyperbots-ai
5
+ website: https://www.hyperbots.com?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf
6
  type: company
7
  location: New York, NY & Bengaluru, India
8
  ---
 
12
 
13
  <p>
14
  <a href="https://huggingface.co/spaces/nchhaya/hyperapi-demo"><b>▶️ Live demo</b></a> ·
15
+ <a href="https://apis.hyperbots.com/dashboard/register?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf"><b>🔑 Get a free API key</b></a> ·
16
+ <a href="https://www.hyperbots.com/request-demo?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf"><b>📅 Request a POC</b></a> ·
17
+ <a href="https://apis.hyperbots.com/sandbox?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf"><b>🧪 Try the sandbox</b></a> ·
18
+ <a href="https://apis.hyperbots.com/docs?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf"><b>📚 Docs</b></a> ·
19
  <a href="https://huggingface.co/spaces/hyperbots-inc/HyperAPI"><b>🧾 HyperAPI Space</b></a> ·
20
  <a href="https://huggingface.co/collections/hyperbots-inc/hyperapi-enterprise-document-intelligence-6af6c8764547d894d4e1a3c4"><b>🗂 Collection</b></a>
21
  </p>
 
36
 
37
  Every response includes per-field confidence, source boxes, document-level checks (for example, line items must add up to the total), and `request_id`, `model_used`, duration and page count for audit. You can run calls sync, async (`X-Async`) or through the Batch API with webhooks. Results are cached for 24 hours, and cached re-runs are not billed.
38
 
39
+ [Get a free key](https://apis.hyperbots.com/dashboard/register?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf) (30 pages/month, no credit card), set `HYPERAPI_KEY` and follow the [quickstart](https://apis.hyperbots.com/docs/quickstart?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf) to use the SDK or REST API:
40
 
41
  ```python
42
  from hyperapi import HyperAPIClient
 
84
 
85
  ## The models
86
 
87
+ HyperAPI runs on **HyperLM**, Hyperbots' mixture-of-experts document stack. It combines small, vision and large language models with multimodal encoders for layout, text and image, and decoders specialised by task and field. HyperLM is trained on **35M+ real-world documents and 0.5B synthetic samples** and retrained continuously. Related research: [**DocuLite**](https://www.hyperbots.com/research/breaking-the-annotation-barrier-with-doculite?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf) (4th Deployable AI Workshop, AAAI 2026) shows how to adapt small LLMs and VLMs to invoice extraction with synthetic data instead of human annotation.
88
 
89
  ## Security and enterprise deployment
90
 
91
  ISO 27001, SOC 1 Type 2 and SOC 2 Type 2. Documents are processed in memory and deleted when the run completes unless you enable retention, and customer data is never used for training. Redaction can run before a document reaches any model. BYOK, IP allow-listing, SSO (Okta, Entra ID, Google Workspace, OneLogin), role-based access and full audit trails are available. Enterprise evaluations run as a POC on your own sample documents, scored field by field against an answer key.
92
 
93
+ ## 🚀 Get started
94
+
95
+ | You want to… | Do this |
96
+ |---|---|
97
+ | See it work, no code | [Live demo](https://huggingface.co/spaces/nchhaya/hyperapi-demo): classify, parse, extract, redact or split a sample |
98
+ | Benchmark it yourself | [Get a free API key](https://apis.hyperbots.com/dashboard/register?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf) (30 pages a month) and score it on our [open datasets](https://huggingface.co/collections/hyperbots-inc/hyperapi-enterprise-document-intelligence-6af6c8764547d894d4e1a3c4) |
99
+ | Test it on your own documents | [Request a proof of concept](https://www.hyperbots.com/request-demo?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf): we score HyperAPI field by field on a sample of your real documents |
100
+ | Connect your agents over MCP | Email [hyperapi-support@hyperbots.com](mailto:hyperapi-support@hyperbots.com) for access |
101
+
102
  ## 📰 Read more
103
 
104
  - [Introducing HyperAPI: one API for every enterprise document, plus ten open benchmarks](https://huggingface.co/blog/nchhaya/introducing-hyperapi)
105
+ - [How to benchmark document AI on enterprise documents without sharing a single real one](https://huggingface.co/blog/nchhaya/benchmark-document-ai-synthetic-datasets): a step-by-step scorecard for parsing, extraction, classification, splitting and redaction
106
  - [Live demo Space](https://huggingface.co/spaces/nchhaya/hyperapi-demo): try classify, parse, extract, redact and split on synthetic examples or your own test file
107
 
108
  ## About Hyperbots
109
 
110
  Hyperbots builds AI agents for finance and accounting (procure-to-pay, order-to-cash and the CFO office). HyperAPI is the same document intelligence that runs inside those agents, offered as APIs. The team has 150+ people, including 50 machine-learning scientists, with 50+ patents and 100+ publications.
111
 
112
+ [apis.hyperbots.com](https://apis.hyperbots.com?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf) · [hyperbots.com](https://www.hyperbots.com?utm_source=huggingface&utm_medium=org_card&utm_campaign=hyperapi_hf) · [GitHub SDK](https://github.com/hyprbots/hyperapi-sdk) · [LinkedIn](https://www.linkedin.com/company/hyperbots-inc) · [X](https://x.com/hyprbots) · [hyperapi-support@hyperbots.com](mailto:hyperapi-support@hyperbots.com) · [research@hyperbots.com](mailto:research@hyperbots.com)