agentspace

द्वारा agentspace-so

देखें कि आपका AI एजेंट क्या कर रहा है, कहीं से भी। एजेंट लिखता रहता है — लॉग, कोड, जनरेटेड आउटपुट, स्क्रीनशॉट, आर्टिफैक्ट्स। एक कमांड फ़ोल्डर को एक लाइव URL में बदल देता है जिसे आप (या कोई सहकर्मी) किसी भी ब्राउज़र में खोलकर फ़ाइलों को विकसित होते देख सकते हैं, जगह पर संपादित कर सकते हैं, या टिप्पणी कर सकते हैं — कोई सिंक, कोई ज़िप, कोई खाता नहीं। वर्कस्पेस 24 घंटे अनाम

npx skills add https://github.com/agentspace-so/skills --skill agentspace

🪢 Agentspace

See what your agent is doing — from anywhere.

Your agent keeps writing — logs, code, generated outputs. You open a URL and watch the folder evolve in the browser. No sync, no zip, no account.

  1. Tell the agent to share any local folder or file.
  2. The agent returns a URL — anyone opens it in the browser, no signup.

agentspace.so · GitHub · npm @agentspace-so/ascli

What you can share

Folders, single files, generated code, test output, build logs, screenshots, PDFs, reports, dashboards, prototypes — any local artifact.

How it works

  • One command (ascli share <path>) creates an anonymous workspace and returns a link.
  • Anyone opens the link — reads, comments, or edits directly in the browser.
  • Anonymous workspaces live 24 hours. One email claim makes them permanent.
  • Hosted on Cloudflare's edge network — links load fast worldwide.

Data handling

  • Only the path the user explicitly names is uploaded. Do not default to the current working directory unless the user clearly says so.
  • All network traffic goes to agentspace.so only.
  • The skill does not read environment variables, shell history, or files outside the path the user specifies.

Choose the CLI path

  1. If ascli is already on PATH, use it directly.
  2. Else if npm is available, install once with npm install -g @agentspace-so/ascli@latest, or run without installing via npx @agentspace-so/ascli@latest <command>.
  3. If neither ascli nor npm is available, stop and tell the user to install Node.js from nodejs.org first.

Do not pipe a remote script into a shell to install.

Share a path

  • Ask the user which folder or file to share if they have not named one explicitly. Do not assume ..
  • Run ascli share <path> --permission edit with the user-specified path.
  • If the user asks for view-only access, use --permission view.
  • share handles an unbound folder by creating a temporary workspace, syncing once, and returning a link — no separate sync step is needed.
  • Return the share URL directly to the user exactly as the CLI prints it.

Guardrails

  • Do not invent claim URLs, workspace URLs, or share URLs. Only return what the CLI prints.
  • Do not require a global install if npx already works.
  • Do not move the user into a different project just to use agentspace.so.
  • If the user asks to "share this folder" and the target is ambiguous, confirm the exact path before running.
  • If you need exact command variants, read references/commands.md.

agentspace-so की और Skills

ai-avatar-video
agentspace-so
Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced...
videocreativemedia
ai-music
agentspace-so
We need to translate the given English text into Hindi, preserving the name "ai-music" if it appears, but it does not appear in the text. The text describes an agent skill for generating AI music via RunComfy CLI. We must not add any extra commentary, labels, or formatting. Just the translation. The text includes product names: RunComfy, ElevenLabs AI Music Generation, ACE Step, ACE Step 1.5, StepFun-AI. Also technical terms: CLI, premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s, open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper, audio-inpaint, audio-outpaint, regenerate a time range, extend a track before or after. Also "Picks the right..." is incomplete but we translate as is. We need to output only the translated text. Use Hindi script. Ensure numbers, units, prices, and technical terms are preserved as is.
creativeaudioapi
video-edit
agentspace-so
RunComfy पर मौजूद वीडियो को संपादित करें — यह स्किल एक स्मार्ट राउटर है जो उपयोगकर्ता के इरादे को RunComfy कैटलॉग में सही एडिट मॉडल से मिलाता है। Wan 2.7 Edit-Video (सामान्य रीस्टाइल / बैकग्राउंड स्वैप / पैकेजिंग स्वैप, पहचान और गति संरक्षण), Kling 2.6 Pro Motion Control (एक रेफरेंस वीडियो से लक्ष्य कैरेक्टर पर सटीक गति स्थानांतरित करना), या Lucy Edit Restyle (हल्का पहचान-स्थिर रीस्टाइल / आउटफिट स्वैप
videocreativemedia
relight
agentspace-so
Relight a still image — change the lighting setup, color temperature, direction, or mood — on RunComfy via the `runcomfy` CLI. Routes to Qwen Edit 2509's dedicated `relight` LoRA endpoint for purpose-built relighting, with fallback to identity-preserving edit endpoints (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when prose lighting language is enough. Use for product relighting (studio softbox → window light), portrait mood shift (overcast → golden hour), or color-grade change....
creativeimagemedia
kling-3-0
agentspace-so
RunComfy पर Kling 3.0 वीडियो जनरेशन। Kling 3.0 (जिसे Kling V3.0 भी कहा जाता है) Kuaishou Technology का तीसरी पीढ़ी का मल्टी-शॉट वीडियो मॉडल है जिसमें मूल सिंक्रोनाइज़्ड ऑडियो और शॉट्स में सुसंगत चरित्र पहचान है। यह स्किल सभी छह Kling 3.0 एंडपॉइंट्स को कवर करता है, जो तीन रेंडरिंग टियर (Standard, Pro, 4K) और दो मोड (टेक्स्ट-टू-वीडियो, इमेज-टू-वीडियो) में फैले हुए
creativevideomedia
runcomfy-cli
agentspace-so
We need to translate the given English text into Hindi. The text describes a CLI tool called runcomfy-cli (name preserved). The instruction says to translate only the text inside <text>, and not include the name unless it appears in the source text. The name "runcomfy-cli" is not in the source text; the source mentions "runcomfy CLI" but that's different. The name to preserve is "runcomfy-cli" but it's not in the source. So we just translate the text. We need to preserve product names, protocol names, URLs, numbers, technical terms. So "RunComfy", "CLI", "ControlNet", "LoRA" etc. should remain as is. Also "image generation", "video generation" etc. are technical terms but can be translated? The instruction says preserve technical terms. Typically, terms like "image generation" might be translated if common, but to be safe, we can keep them in English or use common Hindi equivalents. However, the instruction says "preserve technical terms" -
creativemediaapi
happyhorse-1-0
agentspace-so
RunComfy पर HappyHorse 1.0 के साथ टेक्स्ट-टू-वीडियो जनरेट करें। HappyHorse 1.0 की खूबियों (आर्टिफिशियल एनालिसिस वीडियो एरिना में #1, नेटिव 1080p के साथ इन-पास सिंक्रोनाइज़्ड ऑडियो, मल्टी-शॉट कैरेक्टर कंसिस्टेंसी, 6-भाषा प्रॉम्प्ट सपोर्ट), अवधि / आस्पेक्ट-रेटियो / रिज़ॉल्यूशन स्कीमा, और Wan 2.7 / Seedance 2 / LTX 2 पर कब रूट करना है, का दस्तावेज़ीकरण करता है।
creativevideomedia
ai-image-generation
agentspace-so
Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits,...
creativemediaimage