open-agents-ai 0.184.29 → 0.184.30

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 +85 -0
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -22,6 +22,45 @@ npm i -g open-agents-ai && oa
22
22
 
23
23
  An autonomous multi-turn tool-calling agent that reads your code, makes changes, runs tests, and fixes failures in an iterative loop until the task is complete. First launch auto-detects your hardware and configures the optimal model with expanded context window automatically.
24
24
 
25
+ ## Table of Contents
26
+
27
+ - [The Organism, Not the Cortex](#the-organism-not-the-cortex)
28
+ - [How It Works](#how-it-works)
29
+ - [Features](#features)
30
+ - [Enterprise & Headless Mode](#enterprise--headless-mode)
31
+ - [Architecture](#architecture)
32
+ - [Context Engineering](#context-engineering)
33
+ - [Model-Tier Awareness](#model-tier-awareness)
34
+ - [Auto-Expanding Context Window](#auto-expanding-context-window)
35
+ - [Tools (61)](#tools-61)
36
+ - [Ralph Loop — Iteration-First Design](#ralph-loop--iteration-first-design)
37
+ - [Task Control](#task-control)
38
+ - [COHERE Cognitive Framework](#cohere-cognitive-framework)
39
+ - [Context Compaction — Research-Backed Memory Management](#context-compaction--research-backed-memory-management)
40
+ - [Personality Core — SAC Framework Style Control](#personality-core--sac-framework-style-control)
41
+ - [Emotion Engine — Affective State Modulation](#emotion-engine--affective-state-modulation)
42
+ - [Voice Feedback (TTS)](#voice-feedback-tts)
43
+ - [Listen Mode — Live Bidirectional Audio](#listen-mode--live-bidirectional-audio)
44
+ - [Vision & Desktop Automation (Moondream)](#vision--desktop-automation-moondream)
45
+ - [Interactive TUI](#interactive-tui)
46
+ - [Telegram Bridge — Sub-Agent Per Chat](#telegram-bridge--sub-agent-per-chat)
47
+ - [x402 Payment Rails & Nexus P2P](#x402-payment-rails--nexus-p2p)
48
+ - [Sponsored Inference — Share Your GPU With the World](#sponsored-inference--share-your-gpu-with-the-world)
49
+ - [Dream Mode — Creative Idle Exploration](#dream-mode--creative-idle-exploration)
50
+ - [Blessed Mode — Infinite Warm Loop](#blessed-mode--infinite-warm-loop)
51
+ - [Code Sandbox](#code-sandbox)
52
+ - [Structured Data Tools](#structured-data-tools)
53
+ - [Multi-Provider Web Search](#multi-provider-web-search)
54
+ - [Task Templates](#task-templates)
55
+ - [Human Expert Speed Ratio](#human-expert-speed-ratio)
56
+ - [Cost Tracking & Session Metrics](#cost-tracking--session-metrics)
57
+ - [Configuration](#configuration)
58
+ - [Model Support](#model-support)
59
+ - [Supported Inference Providers](#supported-inference-providers)
60
+ - [Evaluation Suite](#evaluation-suite)
61
+ - [AIWG Integration](#aiwg-integration)
62
+ - [License](#license)
63
+
25
64
  ## The Organism, Not the Cortex
26
65
 
27
66
  An LLM is a high-bandwidth associative generative core — closer to a cortex-like prior than to a complete agent. Its weights contain broad latent structure, but they do not by themselves give you situated continuity, durable task state, calibrated action policies, or grounded memory management. Open Agents treats the model as one organ inside a larger organism. The framework provides the rest: sensors, effectors, memory stores, routing, gating, evaluation, and persistence.
@@ -158,6 +197,52 @@ D8AgCTrxpDKD5meJ2bpAfVwcST3NF3EPuy9xczYycnXn
158
197
  0x81Ce81F0B6B5928E15d3a2850F913C88D07051ec
159
198
  ```
160
199
 
200
+ ## Enterprise & Headless Mode
201
+
202
+ Run Open Agents as a headless service for CI/CD pipelines, automation, and enterprise deployments.
203
+
204
+ ### Non-Interactive Mode
205
+
206
+ ```bash
207
+ oa "fix all lint errors" --non-interactive # Run task, exit when done
208
+ oa "generate API docs" --json # Structured JSON output (no ANSI)
209
+ oa "run security audit" --background # Detached background job
210
+ ```
211
+
212
+ ### Background Jobs
213
+
214
+ ```bash
215
+ oa "migrate database" --background # Returns job ID immediately
216
+ oa status job-abc123 # Check job progress
217
+ oa jobs # List all running/completed jobs
218
+ ```
219
+
220
+ Jobs run as detached processes — survive terminal disconnection. Output saved to `.oa/jobs/{id}.json`.
221
+
222
+ ### JSON Output Mode
223
+
224
+ With `--json`, all output is structured NDJSON:
225
+ ```json
226
+ {"type":"tool_call","tool":"file_edit","args":{"path":"src/api.ts"},"timestamp":"..."}
227
+ {"type":"tool_result","tool":"file_edit","result":"OK","timestamp":"..."}
228
+ {"type":"task_complete","summary":"Fixed 3 lint errors","timestamp":"..."}
229
+ ```
230
+
231
+ Pipe to `jq`, ingest into monitoring systems, or feed to other agents.
232
+
233
+ ### Process Management
234
+
235
+ ```bash
236
+ /destroy processes # Kill orphaned OA processes (local project)
237
+ /destroy processes --global # Kill ALL orphaned OA processes system-wide
238
+ ```
239
+
240
+ Shows per-process RAM and CPU usage before killing. Detects: cloudflared tunnels, nexus daemons, headless Chrome, TTS servers, Python REPLs, stale OA instances.
241
+
242
+ ### Enterprise Licensing
243
+
244
+ Free for non-commercial use under CC-BY-NC-4.0. For enterprise/commercial licensing, contact [zoomerconsulting.com](https://zoomerconsulting.com).
245
+
161
246
  ## Architecture
162
247
 
163
248
  The core is `AgenticRunner` — a multi-turn tool-calling loop with structured context assembly:
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "open-agents-ai",
3
- "version": "0.184.29",
3
+ "version": "0.184.30",
4
4
  "description": "AI coding agent powered by open-source models (Ollama/vLLM) \u2014 interactive TUI with agentic tool-calling loop",
5
5
  "type": "module",
6
6
  "main": "./dist/index.js",