@openenthrium/oe-runtime 1.5.9 → 1.6.1

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.
Files changed (2) hide show
  1. package/README.md +182 -44
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -1,9 +1,12 @@
1
- # OE Runtime · `@openenthrium/oe-runtime`
1
+ # Open Enthrium AI Agent Runtime · `@openenthrium/oe-runtime`
2
2
 
3
- **Run AI agents against 2,600+ enterprise data sources — databases, APIs, files, SSH, messaging, and more. One binary. One YAML agent. One config file.**
3
+ **OE Runtime · Standalone AI Agent Executor · Apache-2.0 · Windows · Linux · macOS**
4
+
5
+ Run AI agents against any enterprise data source — no cloud, no platform, just a single binary.
4
6
 
5
7
  [![npm](https://img.shields.io/npm/v/@openenthrium/oe-runtime?color=4f46e5)](https://www.npmjs.com/package/@openenthrium/oe-runtime)
6
8
  [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-4f46e5.svg)](https://github.com/enthrium/open-enthrium-ai-agent-runtime/blob/main/LICENSE)
9
+ [![GitHub Release](https://img.shields.io/github/v/release/enthrium/open-enthrium-ai-agent-runtime?color=4f46e5&label=latest)](https://github.com/enthrium/open-enthrium-ai-agent-runtime/releases)
7
10
  [![Website](https://img.shields.io/badge/Website-openenthrium.com-4f46e5)](https://www.openenthrium.com/runtime.html)
8
11
  [![Discord](https://img.shields.io/badge/Discord-Community-5865F2?logo=discord&logoColor=white)](https://discord.com/invite/vWsZ24Msn)
9
12
 
@@ -11,13 +14,29 @@
11
14
 
12
15
  ## What is OE Runtime?
13
16
 
14
- OE Runtime is a standalone binary that reads a declarative YAML agent file, connects to your enterprise data sources, and runs an AI-powered workflow — locally or as an HTTP API server. No Python, no LangChain, no code.
17
+ Open Enthrium AI Agent Runtime (OE Runtime) is a standalone, cross-platform binary that reads a declarative YAML agent file, connects to your enterprise data sources, and runs an AI-powered workflow — locally or as an HTTP API server.
18
+
19
+ - **No LangChain. No Python. No code.** Agents are plain YAML files.
20
+ - **No install.** Single binary for Windows, Linux, and macOS. No Node.js, no Docker on the target machine.
21
+ - **45+ connector categories.** PostgreSQL, MySQL, MongoDB, S3, Slack, GitHub, SSH, REST API, Kafka, and 2,600+ more — all built in.
22
+ - **HTTP server mode.** `--serve` turns the runtime into a persistent API server any app can call.
23
+ - **Self-hosted.** Runs entirely on your own machine. No call-home. Own your data.
24
+
25
+ ---
26
+
27
+ ## Sample Library
28
+
29
+ Download [oe-runtime-samples.zip](https://github.com/enthrium/open-enthrium-ai-agent-runtime/releases/latest/download/oe-runtime-samples.zip) for 21 ready-to-run starter kits — each with a complete `agent.yaml` + `oe-config.json`:
30
+
31
+ `sql-databases` · `nosql-cache` · `file-storage` · `cloud-drives` · `email` · `team-messaging` · `telegram` · `productivity-crm` · `rest-api` · `graphql` · `ssh` · `message-queues` · `iot-messaging` · `web-search` · `ocr-vision` · `image-generation` · `speech-audio` · `video-generation` · `music-generation` · `blockchain-web3` · `directory-identity`
15
32
 
16
33
  ---
17
34
 
18
35
  ## Quick Start
19
36
 
20
- **1. Create your config file** (`oe-config.json`)
37
+ No binary download needed — `npx` handles everything automatically.
38
+
39
+ **1. Edit `oe-config.json`** with your LLM key and connector credentials
21
40
 
22
41
  ```json
23
42
  {
@@ -28,45 +47,81 @@ OE Runtime is a standalone binary that reads a declarative YAML agent file, conn
28
47
  },
29
48
  "connectors": [
30
49
  {
31
- "connection_name": "my-db",
50
+ "connection_name": "My Database",
32
51
  "connection_type": "postgresql",
33
52
  "host": "localhost",
34
53
  "port": 5432,
35
54
  "database": "mydb",
36
55
  "user": "postgres",
37
- "password": "secret"
56
+ "password": "YOUR_DB_PASSWORD"
57
+ },
58
+ {
59
+ "connection_name": "My Telegram Bot",
60
+ "connection_type": "telegram",
61
+ "baseUrl": "https://api.telegram.org/botYOUR_BOT_TOKEN"
38
62
  }
39
63
  ],
40
64
  "server": {
41
- "enabled": true,
65
+ "enabled": false,
42
66
  "port": 3333,
43
67
  "apiKey": "your-secret"
44
68
  }
45
69
  }
46
70
  ```
47
71
 
48
- **2. Create your agent file** (`agent.yaml`)
72
+ **2. Edit `agent.yaml`** if needed — adjust the instructions or steps for your use case
73
+
74
+ Agents are plain YAML files. No Python. No framework to learn.
49
75
 
50
76
  ```yaml
51
77
  name: DB Summary Agent
52
- description: Summarises recent activity in the database
53
- instructions: You are a data analyst. Use the available tools to answer questions about the database.
78
+ description: Queries a database and sends a summary to Telegram
79
+ instructions: |
80
+ You are a data analyst. Query the database for key metrics,
81
+ summarise the findings clearly, and send the report to Telegram.
82
+ Complete all steps fully before writing your report.
54
83
  steps:
55
- - name: Check recent orders
56
- content: Query the last 10 orders and summarise the results.
84
+ - name: Query metrics
85
+ content: |
86
+ Run exactly this query against My Database, no other queries:
87
+ SELECT table_name FROM information_schema.tables
88
+ WHERE table_schema = 'public';
89
+ Summarise the results.
90
+ - name: Get chat ID
91
+ content: |
92
+ Call My Telegram Bot:
93
+ GET /getUpdates with params: { "limit": "1" }
94
+ Extract the chat_id from the most recent message.
95
+ - name: Send report
96
+ content: |
97
+ Send the summary via My Telegram Bot:
98
+ POST /sendMessage with body:
99
+ {
100
+ "chat_id": "<chat_id from previous step>",
101
+ "text": "<your summary>",
102
+ "parse_mode": "Markdown"
103
+ }
57
104
  connectors:
58
- - connection_name: my-db
105
+ - connection_name: My Database
59
106
  connection_type: postgresql
107
+ - connection_name: My Telegram Bot
108
+ connection_type: telegram
60
109
  ```
61
110
 
62
- **3. Run it**
111
+ ### YAML Agent Reference
63
112
 
64
- macOS / Linux:
65
- ```bash
66
- npx -y @openenthrium/oe-runtime agent.yaml --config oe-config.json
67
- ```
113
+ | Field | Required | Description |
114
+ |---|---|---|
115
+ | `name` | No | Display name shown in terminal |
116
+ | `description` | No | Short description |
117
+ | `instructions` | Yes | System prompt — what the agent does and how |
118
+ | `params` | No | Named parameters; substituted via `{{name}}` in prompt and steps |
119
+ | `connectors` | No | Connector references matched to credentials in `oe-config.json` |
120
+ | `steps` | No | Named workflow steps injected sequentially into the system prompt |
121
+ | `maxRounds` | No | Max LLM tool-call iterations (default: 25) |
122
+
123
+ **3. Run it**
68
124
 
69
- Windows:
70
125
  ```bash
71
126
  npx -y @openenthrium/oe-runtime agent.yaml --config oe-config.json
72
127
  ```
@@ -86,7 +141,35 @@ npx -y @openenthrium/oe-runtime agent.yaml --config oe-config.json
86
141
 
87
142
  ---
88
143
 
89
- ## HTTP Server Endpoints
144
+ ## HTTP Server Mode
145
+
146
+ Turn the runtime into a persistent HTTP API — call agents from mobile apps, web services, or any HTTP client.
147
+
148
+ **Step 1 — Enable server mode in `oe-config.json`:**
149
+
150
+ ```json
151
+ {
152
+ "llm": { "provider": "openai", "apiKey": "sk-...", "model": "gpt-4o" },
153
+ "server": {
154
+ "enabled": true,
155
+ "port": 3333,
156
+ "apiKey": "your-secret-api-key"
157
+ },
158
+ "connectors": [ ... ]
159
+ }
160
+ ```
161
+
162
+ > Set **`"enabled": true`** to activate server mode on startup.
163
+
164
+ **Step 2 — Start in serve mode:**
165
+
166
+ ```bash
167
+ npx -y @openenthrium/oe-runtime --serve --config oe-config.json
168
+ # 🚀 OE Runtime Server v1.5.9
169
+ # Listening http://localhost:3333
170
+ ```
171
+
172
+ ### Endpoints
90
173
 
91
174
  All endpoints require the `x-api-key` header when `server.apiKey` is set in your config.
92
175
 
@@ -101,7 +184,7 @@ All endpoints require the `x-api-key` header when `server.apiKey` is set in your
101
184
  {
102
185
  "yaml": "name: Hi\nsteps:\n - name: Greet\n content: Say hi!",
103
186
  "params": {},
104
- "input": "optional user message"
187
+ "input": "Run"
105
188
  }
106
189
  ```
107
190
 
@@ -110,7 +193,7 @@ All endpoints require the `x-api-key` header when `server.apiKey` is set in your
110
193
  {
111
194
  "file": "/path/to/agent.yaml",
112
195
  "params": { "topic": "AI trends" },
113
- "input": "optional user message"
196
+ "input": "Run"
114
197
  }
115
198
  ```
116
199
 
@@ -128,50 +211,105 @@ curl http://localhost:3333/health -H "x-api-key: your-secret"
128
211
  curl -X POST http://localhost:3333/run \
129
212
  -H "x-api-key: your-secret" \
130
213
  -H "Content-Type: application/json" \
131
- -d '{"yaml":"name: Hi\nsteps:\n - name: Greet\n content: Say hi!"}'
214
+ -d '{"yaml":"name: Hi\nsteps:\n - name: Greet\n content: Say hi!","input":"Run"}'
132
215
 
133
216
  # Run agent from file
134
217
  curl -X POST http://localhost:3333/run-file \
135
218
  -H "x-api-key: your-secret" \
136
219
  -H "Content-Type: application/json" \
137
- -d '{"file":"/path/to/agent.yaml","params":{"topic":"AI trends"}}'
220
+ -d '{"file":"/path/to/agent.yaml","params":{"topic":"AI trends"},"input":"Run"}'
221
+ ```
222
+
223
+ ---
224
+
225
+ ## Binary vs Node.js Mode
226
+
227
+ Both **`npx @openenthrium/oe-runtime`** and the standalone binary exclude Oracle, MSSQL, SQLite, and Snowflake — these use native C++ addons that cannot be bundled into a single executable. npx downloads the same binary under the hood, so it has the same limitation.
228
+
229
+ If you need any of these four, run with Node.js directly instead:
230
+ ```bash
231
+ git clone https://github.com/enthrium/open-enthrium-ai-agent-runtime.git
232
+ cd open-enthrium-ai-agent-runtime/server
233
+ yarn install
234
+ node cli/index.js agent.yaml --config oe-config.json
235
+ # or serve mode
236
+ node cli/index.js --serve --config oe-config.json
138
237
  ```
139
238
 
239
+ All other connectors (PostgreSQL, MySQL, MongoDB, Redis, S3, Slack, GitHub, REST API, SSH, etc.) work directly with npx — no Node.js clone required.
240
+
140
241
  ---
141
242
 
142
- ## Supported Connectors
243
+ ## Connector Catalog
143
244
 
144
- **2,600+ connectors across 45+ categories:**
245
+ **2,600+ connectors across 45+ categories** — built in, no custom code required.
145
246
 
146
247
  | Category | Examples |
147
248
  |---|---|
148
249
  | **SQL Databases** | PostgreSQL, MySQL, MSSQL, Oracle, SQLite, Snowflake, BigQuery, Redshift |
149
- | **NoSQL / Cache** | MongoDB, Redis, Elasticsearch, DynamoDB, Cassandra |
150
- | **Object Storage** | AWS S3, GCS, Azure Blob, MinIO, Cloudflare R2 |
151
- | **Cloud Drives** | Google Drive, OneDrive, Dropbox, Box |
152
- | **Filesystem** | Local directories — list, read, write, search |
153
- | **Email** | Gmail, Outlook, Zoho Mail, SMTP |
250
+ | **NoSQL / Cache** | MongoDB, Redis, Elasticsearch, DynamoDB, Cassandra, Couchbase |
251
+ | **Object Storage** | AWS S3, GCS, Azure Blob, MinIO, Cloudflare R2, Backblaze B2 |
252
+ | **Cloud Drives** | Google Drive, OneDrive, SharePoint, Dropbox, Box |
253
+ | **Filesystem** | Local directories — list, read, write, search files |
254
+ | **Email** | Gmail, Outlook, Zoho Mail, SMTP, IMAP, SendGrid |
154
255
  | **Team Messaging** | Slack, Microsoft Teams, Discord, Telegram |
155
- | **CRM** | HubSpot, Salesforce, Notion, Airtable |
256
+ | **CRM / Productivity** | HubSpot, Salesforce, Notion, Airtable, Confluence |
156
257
  | **Issue Tracking** | GitHub, Jira, GitLab, Linear |
157
- | **REST API** | Any HTTP/REST endpoint |
158
- | **SSH / SFTP** | Remote command execution, file transfer |
159
- | **Message Queues** | Kafka, AWS SQS, Google Pub/Sub, RabbitMQ |
160
- | **+ more** | LDAP, OCR, Image Generation, Healthcare, ERP, Web3, ... |
258
+ | **REST API** | Any HTTP/REST endpoint — bearer, API key, basic auth |
259
+ | **GraphQL** | Any GraphQL endpoint |
260
+ | **SSH / SFTP** | Remote command execution and file transfer |
261
+ | **Message Queues** | Kafka, AWS SQS, Azure Service Bus, Google Pub/Sub, RabbitMQ |
262
+ | **IoT / MQTT** | MQTT brokers, AWS IoT |
263
+ | **Search** | Perplexity, Google Custom Search, Bing |
264
+ | **LDAP / Directory** | Active Directory, OpenLDAP, Azure AD |
265
+ | **OCR / Vision** | Azure Vision, Google Vision, AWS Textract |
266
+ | **Image Generation** | OpenAI gpt-image-1, FLUX, Stable Diffusion, Ideogram |
267
+ | **Speech & Audio** | ElevenLabs, OpenAI TTS, Azure Speech, Google TTS |
268
+ | **Video Generation** | Runway, Kling, Pika |
269
+ | **Music Generation** | kie.ai, Udio |
270
+ | **Web3 / Blockchain** | Ethereum, Polygon, Solana via web3.js / ethers.js |
271
+ | **Helpdesk** | Zendesk, Freshdesk, Intercom |
272
+ | **ERP** | SAP, Oracle ERP, Microsoft Dynamics |
273
+ | **+ more** | Healthcare (FHIR), Marketing, Analytics, Finance, HR, E-commerce, ... |
274
+
275
+ ---
276
+
277
+ ## Supported LLM Providers
278
+
279
+ `openai` · `anthropic` · `azure` · `groq` · `gemini` · `ollama` · `mistral` · `deepseek` · `together` · `fireworks` · `bedrock` · and more
280
+
281
+ ---
282
+
283
+ ## Contributing
284
+
285
+ Contributions are welcome. Before opening a PR:
286
+
287
+ - [Open an issue](https://github.com/enthrium/open-enthrium-ai-agent-runtime/issues/new) to discuss the change — especially for new features
288
+ - Fork the repository and branch from `main`
289
+ - Test your changes locally
290
+ - [Open a PR](https://github.com/enthrium/open-enthrium-ai-agent-runtime/compare) with a clear description of what and why
291
+
292
+ Where contributions are most valuable:
293
+
294
+ - New connector adapters (`server/src/utils/tools/adapters/`)
295
+ - Agent YAML examples for the community marketplace
296
+ - Bug fixes with clear reproduction steps
161
297
 
162
298
  ---
163
299
 
164
- ## Links
300
+ ## Part of Open Enthrium
301
+
302
+ OE Agent Runtime is the open-source standalone execution layer of the [Open Enthrium](https://openenthrium.com) platform.
165
303
 
166
- - [Full Documentation](https://www.openenthrium.com/runtime.html)
167
- - [GitHub Repository](https://github.com/enthrium/open-enthrium-ai-agent-runtime)
168
- - [Sample Agents](https://github.com/enthrium/open-enthrium-ai-agent-runtime/releases/latest/download/oe-runtime-samples.zip) — 20 ready-to-use agent YAML files
169
- - [Discord Community](https://discord.com/invite/vWsZ24Msn)
170
- - [OE Platform](https://www.openenthrium.com/platform.html) — full web app with Agent Builder, RAG, workspaces
171
- - [OE MCP Server](https://www.openenthrium.com/mcp.html) — connect Claude Code, Cursor & Windsurf to enterprise data
304
+ | | |
305
+ |---|---|
306
+ | 🖥️ **Platform** | [open-enthrium-ai-platform](https://github.com/enthrium/open-enthrium-ai-platform) — full web app with workspaces, RAG, Agent Builder, DLP |
307
+ | 🔌 **MCP Server** | [open-enthrium-ai-mcp-server](https://github.com/enthrium/open-enthrium-ai-mcp-server) — connect Claude Code, Cursor, Windsurf to enterprise data |
308
+ | 🌐 **Website** | [openenthrium.com](https://openenthrium.com) |
172
309
 
173
310
  ---
174
311
 
175
312
  ## License
176
313
 
177
- [Apache-2.0](https://github.com/enthrium/open-enthrium-ai-agent-runtime/blob/main/LICENSE) — free to use, modify, and deploy for any purpose including commercial use.
314
+ [Apache-2.0](https://github.com/enthrium/open-enthrium-ai-agent-runtime/blob/main/LICENSE) — free to use, modify, and deploy for any purpose, including commercial use.
315
+ No usage limits. No telemetry. No call-home.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@openenthrium/oe-runtime",
3
- "version": "1.5.9",
3
+ "version": "1.6.1",
4
4
  "description": "OE Runtime - run AI agents against 2,600+ enterprise data sources. One binary, one YAML agent, one config file.",
5
5
  "homepage": "https://www.openenthrium.com/runtime.html",
6
6
  "repository": {