2025-05-31 - 2026-05-31
Overview
2 Pull requests merged by 1 user
Merged
#7 feat(ocr): add /ocr endpoint for text extraction
Merged
#6 feat(exec): add low-friction shell execution endpoint
21 Issues closed from 1 user
Closed
#22 Add better target-debug overlays and candidate inspection
Closed
#21 Strengthen post-action verification for real UI workflows
Closed
#24 Standardize response schemas across endpoints
Closed
#18 Improve OCR reliability on dense real-world UIs
Closed
#19 Add structured text-targeted control lookup/click helpers
Closed
#20 Add first-class window-to-display placement actions
Closed
#23 Improve handling of small control-strip UIs like OBS
Closed
#15 feat(verify): add compound action+verify flows
Closed
#14 feat(vision): add screenshot diff and stability helpers
Closed
#13 feat(ocr): add higher-level text search helpers on top of OCR
Closed
#16 docs(playbooks): expand agent playbooks beyond Spotify
Closed
#17 docs(skill): explain using OpenClaw image tool with screenshots
Closed
#12 feat(wait): add wait/synchronization endpoints for UI state changes
Closed
#11 feat(window): add window and app lifecycle endpoints
Closed
#10 docs(skill): tighten API examples and /exec usage guidance
Closed
#8 Support Second Screen parameters for agents
Closed
#2 feat(vision): add /find endpoint for template/text target detection
Closed
#3 feat(window): add window management endpoints (list/focus/minimize/close)
Closed
#5 feat(state): add server-side interaction session state
Closed
#4 feat(input): add advanced input primitives (drag, key down/up, hold, gesture profiles)
Closed
#1 feat(ocr): add /ocr endpoint for on-screen text extraction
21 Issues created by 0 users
Opened
#1 feat(ocr): add /ocr endpoint for on-screen text extraction
Opened
#2 feat(vision): add /find endpoint for template/text target detection
Opened
#3 feat(window): add window management endpoints (list/focus/minimize/close)
Opened
#4 feat(input): add advanced input primitives (drag, key down/up, hold, gesture profiles)
Opened
#5 feat(state): add server-side interaction session state
Opened
#8 Support Second Screen parameters for agents
Opened
#10 docs(skill): tighten API examples and /exec usage guidance
Opened
#14 feat(vision): add screenshot diff and stability helpers
Opened
#11 feat(window): add window and app lifecycle endpoints
Opened
#12 feat(wait): add wait/synchronization endpoints for UI state changes
Opened
#13 feat(ocr): add higher-level text search helpers on top of OCR
Opened
#15 feat(verify): add compound action+verify flows
Opened
#16 docs(playbooks): expand agent playbooks beyond Spotify
Opened
#17 docs(skill): explain using OpenClaw image tool with screenshots
Opened
#19 Add structured text-targeted control lookup/click helpers
Opened
#18 Improve OCR reliability on dense real-world UIs
Opened
#20 Add first-class window-to-display placement actions
Opened
#21 Strengthen post-action verification for real UI workflows
Opened
#22 Add better target-debug overlays and candidate inspection
Opened
#23 Improve handling of small control-strip UIs like OBS
Opened
#24 Standardize response schemas across endpoints