open-agents-ai 0.69.4 → 0.70.0

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 (3) hide show
  1. package/README.md +3 -1
  2. package/dist/index.js +1133 -402
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -57,12 +57,14 @@ D8AgCTrxpDKD5meJ2bpAfVwcST3NF3EPuy9xczYycnXn
57
57
 
58
58
  ## Features
59
59
 
60
- - **51 autonomous tools** — file I/O, shell, grep, web search/fetch/crawl, memory (read/write/search), sub-agents, background tasks, image/OCR/PDF, git, diagnostics, vision, desktop automation, browser automation, temporal agency (scheduler/reminders/agenda), structured files, code sandbox, transcription, skills
60
+ - **53 autonomous tools** — file I/O, shell, grep, web search/fetch/crawl, memory (read/write/search), sub-agents, background tasks, image/OCR/PDF, git, diagnostics, vision, desktop automation, browser automation, temporal agency (scheduler/reminders/agenda), structured files, code sandbox, transcription, skills, opencode delegation, cron agents
61
61
  - **Moondream vision** — see and interact with the desktop via Moondream VLM (caption, query, detect, point-and-click)
62
62
  - **Desktop automation** — vision-guided clicking: describe a UI element in natural language, the agent finds and clicks it
63
63
  - **Auto-install desktop deps** — screenshot, mouse, OCR, and image tools auto-install missing system packages (scrot, xdotool, tesseract, imagemagick) on first use
64
64
  - **Parallel tool execution** — read-only tools run concurrently via `Promise.allSettled`
65
65
  - **Sub-agent delegation** — spawn independent agents for parallel workstreams
66
+ - **OpenCode delegation** — offload coding tasks to opencode (sst/opencode) as an autonomous sub-agent with auto-install, progress monitoring, and result evaluation
67
+ - **Long-horizon cron agents** — schedule recurring autonomous agent tasks with goals, completion criteria, execution history, and automatic evaluation (daily code reviews, weekly dep updates, continuous monitoring)
66
68
  - **Ralph Loop** — iterative task execution that keeps retrying until completion criteria are met
67
69
  - **Dream Mode** — creative idle exploration modeled after real sleep architecture (NREM→REM cycles)
68
70
  - **Autoresearch Swarm** — 5-agent GPU experiment loop during REM sleep: Researcher, Monitor, Evaluator, Critic, Flow Maintainer autonomously run ML training experiments, keep improvements, discard regressions