惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

T
The Blog of Author Tim Ferriss
IT之家
IT之家
Engineering at Meta
Engineering at Meta
WordPress大学
WordPress大学
博客园 - 三生石上(FineUI控件)
博客园 - 聂微东
C
Check Point Blog
T
Tailwind CSS Blog
博客园 - Franky
H
Help Net Security
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
Google DeepMind News
Google DeepMind News
博客园 - 叶小钗
J
Java Code Geeks
腾讯CDC
罗磊的独立博客
爱范儿
爱范儿
阮一峰的网络日志
阮一峰的网络日志
Martin Fowler
Martin Fowler
酷 壳 – CoolShell
酷 壳 – CoolShell
I
InfoQ
B
Blog
V
Visual Studio Blog
F
Fortinet All Blogs

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
GitHub - Reloops-App/reloops: Open-source creative asset ...
dheerajbhati · 2026-06-03 · via Hacker News - Newest: "AI"

Reloops Logo

License Tracked total GitHub clones

NEW: run the open-source Reloops DAM locally in minutes


Reloops: An alternative to Frame.io, Brandfolder, Bynder, Canto, Dropbox Replay, Ziflow, Filestage, Google Drive, Airtable, and internal DAM tools.
Reloops offers everything you need to organize creative assets,
generate AI descriptions and tags, manage versions, collect approvals, share collections, and let agents work inside your media library.

DAM  ·  AI Metadata  ·  Search  ·  Collections  ·  Review  ·  Approvals  ·  Share Links  ·  Agent API

Quick Start · Discord · OpenClaw API Skill · Features · Alternative To · Tech Stack

Agent-ready DAM · Self-hosted OSS · License

🔌 See the leading Reloops features

Reloops creative asset workspace

✨ Features

🔎 Find any asset instantly

Search across folders, tags, metadata, status, people, smart descriptions, dates, formats, and version stacks from one focused DAM surface.

Reloops digital asset search

✅ Move creative work from review to approved

Run campaigns through a visual workflow board with upload, folders, filters, bulk selection, review states, assignees, and progress tracking.

Reloops project workflow

🤖 Let AI write searchable metadata

Reloops analyzes creative assets and generates useful descriptions and tags, so teams and agents can find the right media without manual cataloging.

Reloops smart metadata

🌌 Publish client-ready collections

Turn selected assets into polished collections with download access, search, creator context, and a focused browsing experience.

Reloops published collection

🔗 Share work without losing control

Create locked share links with expiration, download permissions, comment permissions, and collection-level access rules.

Reloops share link controls

💬 Collect guest feedback without onboarding

External reviewers can identify themselves, view shared assets, leave comments, and participate in review without joining the whole workspace.

Reloops guest review

🎬 Compare versions side by side

Review old and new cuts together, keep timestamped comments attached to the right version, and upload the next pass from the same screen.

Reloops version comparison

🔑 Invite agents into the DAM

Create developer keys for OpenClaw, OpenAI, Claude, Gemini, Zapier, n8n, Replicate, Runway, and custom agents so automation can operate inside the asset system.

Reloops agent and developer keys

👥 Manage teammates, reviewers, and agents

Keep organization members, roles, pending invites, project reviewers, and API-key agents in one admin workspace.

Reloops team and agent registry

🧠 Assign review work to humans or agents

Keep the full decision thread on the asset, assign the next pass to an agent like OpenClaw, and let the agent reply beside the team.

Reloops agent review thread

🔔 Keep every review event visible

Track feedback, mentions, file updates, review activity, and AI metadata jobs from one notification center.

Reloops notifications

Intro

  • 🗂️ Organize every campaign asset in a self-hosted creative DAM.
  • 🔎 Search across folders, tags, metadata, statuses, people, dates, formats, and version stacks.
  • 🤖 Use AI to generate smart descriptions and tags for images, videos, screenshots, and other creative assets.
  • ✅ Move assets through project workflows from needs review to approved.
  • 💬 Manage versions, comments, assignments, reviewers, approvals, share links, and guest feedback.
  • 🧠 Assign review work to humans or agents and keep the full decision thread on the asset.
  • 🌌 Build dynamic collections for campaigns, clients, teams, launches, and reusable asset groups.
  • 👥 Invite team members to collaborate, comment, review, and approve assets.
  • 🔌 Let AI agents and workflow tools create projects, fetch assets, comment, enrich metadata, and manage shares.
  • ⚡ Perfect for automation with platforms like n8n, Make, Zapier, OpenClaw, and custom agents.

🔁 Alternative To

Reloops is a DAM-first product. Review and approval are built in because creative assets do not stop at storage.

If you are using... Reloops helps you replace or extend it with...
Brandfolder, Bynder, Canto Self-hosted creative DAM, collections, metadata, search, and asset history
Google Drive, Dropbox, Notion, Airtable Purpose-built asset workspaces instead of folders, rows, and scattered comments
Frame.io, Dropbox Replay, Wipster Review, comments, version stacks, approvals, and share links inside the DAM
Ziflow, Filestage, ReviewStudio Structured creative feedback without a heavyweight enterprise approval suite
Zapier, n8n, Make, custom agents Controlled API actors that can participate directly in asset operations
Internal DAM tools Auth, storage, asset views, review UI, share links, API keys, and local workers already wired together

🤖 Agent-ready DAM

  • 🔑 API-key actors can operate inside organization workspaces.
  • 👥 Human teammates, reviewers, and API-key agents can all be assigned asset work.
  • 💬 Agents can receive review assignments and reply in the same comment thread as the team.
  • 🗂️ Agents can list and create workspaces and projects.
  • 🔌 Agents can fetch assets, patch asset status, create comments, and manage share links.
  • 🧩 OpenClaw can use the included openclaw-reloops-api skill; see the OpenClaw API Skill guide.
  • 🤖 The local asset intelligence worker uses AI to generate smart descriptions and tags for assets.
  • 🔁 Generated media can flow back into the same library, collection, review, and approval loop.

🧱 Tech Stack

  • 📦 Pnpm workspaces
  • ⚛️ Vite + React + TypeScript
  • 🟢 Supabase Auth, Postgres, Storage, RLS, and Edge Functions
  • 🤖 Node asset intelligence worker
  • 🔑 API-key agent layer
  • 🐳 Docker for local Supabase services

🚀 Quick Start

Start the full local OSS stack with Docker:

cp .env.example .env
docker compose up --build

Then open http://127.0.0.1:6173. For manual pnpm setup and environment details, see the Local Setup Guide.

🏠 Self-hosted OSS

This repository is the open-source, self-hosted version of Reloops.

  • ✅ Included in OSS:

    • Supabase Auth, Postgres, Storage, and Edge Functions
    • Workspaces, teams, projects, folders, assets, versions, comments, reviews, assignments, and notifications
    • DAM search, collections, metadata filtering, AI-generated smart descriptions and tags, share links, and guest comments
    • API-key agent endpoints for controlled automation inside workspaces
    • Local asset intelligence worker with DB queue polling
    • Local-first setup for running the full product on your machine or own infrastructure
  • ⚠️ Not included in this OSS package:

    • Hosted billing and managed subscription infrastructure
    • Hosted cloud storage integrations beyond local Supabase Storage defaults
    • Hosted workers, QStash, Cloudflare Workers, and commercial deployment infrastructure
    • Managed analytics and managed screenshot capture
    • Managed email delivery; local OSS includes notification data/preferences and local invite handling, but production email delivery is expected to be wired by the self-hosting team
  • 🗄️ Storage and capture model:

    • Uploads use Supabase Storage.
    • Website review works with uploaded or captured screenshots.
    • Asset intelligence runs locally through the worker to generate smart descriptions and tags unless you connect your own production worker setup.

📄 License

This repository's source code is available under the AGPL-3.0 license.