Genfeed

ai.genfeed由 genfeed.ai 發布官方發布者v0.2.13-icons.1更新於 Nov 4, 2026

Create, review and schedule social content from your AI agent. Approval-first.

已驗證Streamable HTTP可網頁執行效率與工作流溝通與協作媒體與設計

概覽

AI 產生的概覽

Genfeed 是託管的內容引擎 MCP 伺服器,讓助理生成符合品牌調性的圖片、影片、文字與音訊,並起草、審核和排程社群內容。

可以做什麼
  • 生成圖片、影片、文字、語音與音訊內容
  • 管理品牌、草稿與既有素材
  • 為已連結的頻道排程與排入發布佇列
  • 檢視發布狀態與分析資料
  • 透過網頁應用程式、CLI、REST API 或經 MCP 連接的助理驅動同一套流程
適用情境
適合希望由助理產出行銷或社群內容並推進到發布階段,同時要求發布前由人工審核的情境。也適合已在使用 Genfeed 或願意自行架設的團隊。
執行需求
遠端端點 mcp.genfeed.ai,需透過瀏覽器 OAuth 授權(必要)。若改為自架,需要 Docker Engine 與 Compose v2、3000、3010、3011、3014 連接埠可用、約 15 GB 磁碟空間,以及透過 OPENROUTER_API_KEY 設定的 OpenRouter API 金鑰;npx 安裝方式另需 Node.js 24 或更新版本。
安裝前請注意
此伺服器可生成媒體並在已連結頻道上排程發布,核准前請先檢查草稿。自架需在 .env 中提供 OpenRouter API 金鑰,且啟動成功不代表供應商餘額或模型存取可用。專案仍在 0.x 階段,版本之間可能有破壞性變更。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Genfeed,將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/ai.genfeed%2Fgenfeed/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "genfeed": {
      "type": "http",
      "url": "https://mcp.genfeed.ai/mcp"
    }
  }
}

README

Genfeed.ai

The open-source content engine your agent can run. Self-host it free or use Cloud.

Create on-brand videos, images and posts, then review and publish to your connected channels. Work in Genfeed or connect the AI agent you already use.

[CI] [Release] [License: AGPL-3.0-or-later] [GitHub stars]

If Genfeed is useful, star it on GitHub ⭐ so others can find it.

[A prompt typed in Genfeed Playground, a real image generated with FLUX 1 Schnell, then approved]

One real generation on a self-hosted instance: prompt, generate, approve. About 20 seconds, unedited apart from trimming.

bash
npx @genfeedai/create my-genfeed

Needs Docker Compose v2 and Node.js 24 or newer. The wizard verifies the release bundle, asks for your OpenRouter API key, then starts it. Install guide: genfeed.ai/self-hosted · docs.genfeed.ai.

[!WARNING] Genfeed is 0.x and under active development. Breaking changes ship with an Upgrade note in the release body; semver becomes strict at v1.0.0.

Self-host it (Community), run it on your Mac (Desktop), or use the hosted product at genfeed.ai (SaaS). Same code, three deployment modes.

Requirements (Community)

  • Docker Engine with the Docker Compose v2 plugin (docker compose version), or Docker Desktop. Both npx @genfeedai/create and the release bundle below need it.
  • Node.js 24 or newer (>=24), only for npx @genfeedai/create.
  • Free host ports 3000 (web), 3010 (API), 3011 (WebSocket) and 3014 (MCP).
  • Plan for at least 15 GB of free disk, plus room for media, backups, and upgrades. This is capacity guidance based on the reported v0.2.15 image footprint; see system requirements.
  • RAM: no minimum is published. Tested on 8 CPU / 15 GiB.
  • Debian 13 provides Compose v2 in its docker-compose package. With Docker CE, install docker-compose-plugin from Docker's apt repository.

See troubleshooting if the app logs P1001: Can't reach database server at postgres:5432.

Quick start (Community)

One command (recommended):

bash
npx @genfeedai/create my-genfeed

It downloads and verifies the release bundle, prompts for your OpenRouter key, then starts the stack. Checksums, auth, providers, and upgrades: self-hosting guide.

Release bundle (no Node.js): set OPENROUTER_API_KEY in .env to a real key from openrouter.ai/keys before starting. The container exits at start without it.

bash
curl -fLO https://github.com/genfeedai/genfeed.ai/releases/latest/download/genfeed-selfhosted.tar.gzcurl -fLO https://github.com/genfeedai/genfeed.ai/releases/latest/download/genfeed-selfhosted.tar.gz.sha256sha256sum -c genfeed-selfhosted.tar.gz.sha256tar -xzf genfeed-selfhosted.tar.gz && cd genfeed-selfhosted-v*cp .env.example .env# Edit .env: set OPENROUTER_API_KEY to your real OpenRouter key, then:docker compose --env-file .env -f compose.yml up -d

On macOS, use shasum -a 256 -c genfeed-selfhosted.tar.gz.sha256 for the checksum step. The API and WebSocket ports bind to 127.0.0.1; a remote browser needs a reverse proxy configured as described in the self-hosting guide.

SurfaceLocal URL
Web UIhttp://localhost:3000
REST APIhttp://localhost:3010
MCP serverhttp://localhost:3014
WebSocketws://localhost:3011 (live agent replies; keep it reachable)

The bundle pins the image for its release, applies Prisma migrations, and seeds one local workspace. No Genfeed Cloud account is required.

For a first generation, do these in order:

  1. Make sure OPENROUTER_API_KEY in .env is a real key (the npx wizard sets it for you). Text generation and the agent need it, and the container refuses to start with an empty or placeholder value. If you change .env later, recreate with the same docker compose up -d command so the container reads the new value.
  2. Open http://localhost:3000/sign-up and create your account with Email & password. Sign-up is on by default (BETTER_AUTH_ENABLED=true in .env), and no email provider is needed. The new account gets its own organization and brand.
  3. Complete onboarding, then start a task or generation.

Startup checks the OpenRouter key's format and rejects empty or placeholder values. A successful boot does not prove provider balance or model access. Settings → API Keys validates each provider key against the provider before saving it.

Let your coding agent install it

Genfeed is driven by agents, so installing it is a task you can hand to one. Paste this into Claude Code, Codex, Cursor, or any agent with shell access:

text
Install Genfeed — the open-source content agent — on this machine, then connectit to yourself over MCP.
1. Check Docker Engine with Compose v2 is available.2. Download the Community bundle:   curl -fLO https://github.com/genfeedai/genfeed.ai/releases/latest/download/genfeed-selfhosted.tar.gz   curl -fLO https://github.com/genfeedai/genfeed.ai/releases/latest/download/genfeed-selfhosted.tar.gz.sha256   sha256sum -c genfeed-selfhosted.tar.gz.sha256   tar -xzf genfeed-selfhosted.tar.gz && cd genfeed-selfhosted-v*   On macOS, use shasum -a 256 -c for the checksum step.   cp .env.example .env3. Ask me for my OpenRouter API key and set it in `.env` as   `OPENROUTER_API_KEY` (a real key; the container exits at start without   it). Then start the stack:   docker compose --env-file .env -f compose.yml up -d   Wait for http://localhost:3000 to answer. Sign-up is open by default; the   seed also creates one organization (slug `default`) and brand.4. For Claude Code, register its dedicated content connector:   claude mcp add --transport http genfeed --scope user http://localhost:3014/mcp/claude5. Open /mcp, select genfeed and complete browser OAuth. For other clients,   configure the standard http://localhost:3014/mcp endpoint and authorize in   the browser; a scoped API-key fallback is available for those clients.6. List the Genfeed tools to confirm the connection, then stop.
Reference: https://github.com/genfeedai/genfeed.ai/blob/master/docs/self-hosting.mdDocs index for agents: https://docs.genfeed.ai/llms.txt

Already on the hosted product? Skip installation and authorize with browser OAuth. Claude uses https://mcp.genfeed.ai/mcp/claude for brands, drafts, existing assets, scheduling and analytics; create media in Genfeed Playground. Other clients use https://mcp.genfeed.ai/mcp for the full toolset.

The standard MCP preset is approval-first: an agent can generate, draft, and schedule, but publishing waits for a human. What each surface exposes and why is in Agent Surface.

Captured from the real self-hosted app, v0.2.17, 1440×900 dark theme. The posts and the agent conversation are seeded demo content, not a live generation. Regenerate with bun run readme:capture.

[Agent conversation in Genfeed: a brief for a launch week recap and the agent's drafted X and LinkedIn posts]

Agent: a brief in, drafts out. Both posts wait in Publishing for approval.

[Publishing posts list with scheduled, draft and published posts across X, LinkedIn, Instagram, TikTok and YouTube]

Publish: scheduled, draft and published posts in one list.

[Visual workflow editor showing the Research to Content workflow: Search Knowledge, Generate Post Draft, Collect Workflow Output]

Automate: the Research to Content workflow template in the visual editor.

Capabilities

  • Generate images, video, text, voice, and audio with local or bring-your-own-key execution
  • Visual workflow authoring; content library, brand, scheduling, and publishing
  • Drive the same loop from the web app, the genfeed CLI, the REST API, or any AI agent over MCP
  • PostgreSQL via Prisma; Redis/BullMQ background work
  • A Community Docker distribution built from the same AGPL source as the hosted image

Availability differs by deployment mode and configured provider. Read Deployment Modes and Execution Boundaries before relying on a feature for a specific distribution.

Deployment modes

ModeWho it is forHow you get it
SaaSHosted multi-tenant productapp.genfeed.ai
CommunitySelf-hosters, one organizationChecksummed GitHub release bundle (quick start above)
DesktopSolo creators on their own MacSigned macOS artifacts from desktop-v* tags

Organization billing ships in every image and is gated at runtime (a *.genfeed.ai host / self-host licence) — see the billing section. Managed inference infrastructure and Fleet/LoRA operations live outside this public repository.

Desktop is macOS-first. Mobile and browser/IDE extension sources live in the tree; this repository does not claim a public store listing for them.

How agents work in this repo

This repository is agent-native: most of its code is written by AI agents under human direction, and the tree is laid out so an agent can be productive from a cold clone.

  • AGENTS.md and CLAUDE.md — operating rules every agent (and human) follows: type safety, UI primitives, serializers, tenancy filters, commit conventions.
  • CONTEXT.md — the glossary. One spelling per concept, used in code, issues, docs, and PRs.
  • .agents/ — durable project memory (rules, ADRs under architecture/ADR-*.md, specs) plus build/dev skills for working on the app. MEMORY.md is the index. skills/ at the repo root is different: those are product/content skills the app ships.
  • Issues carry EARS acceptance criteria (WHEN … THE SYSTEM SHALL …) so an agent can pick one up and know what "done" means. Triage rewrites weak criteria; it never bounces.
  • shipcode:* labels are internal automation. They are visible on issues and PRs; contributors never apply them.
  • Agent-authored PRs are welcome when disclosed in the PR body and a named human is accountable for the description and verification. Undisclosed agent-authored PRs are closed. See CONTRIBUTING.md.

PRs are reviewed by an automated pipeline first, then by the maintainer, who alone merges.

Architecture

Genfeed is a Bun/Turborepo monorepo with Next.js clients, NestJS server workspaces, PostgreSQL/Prisma persistence, and Redis/BullMQ queues. The Community image bundles the web app, API, workers, files, notifications, and MCP runtimes into one container and embeds Redis.

text
apps/  web/                    Next.js product UI (app.genfeed.ai)  marketing/              Next.js marketing site (genfeed.ai)  docs/                   Documentation site  server/                 NestJS services and shared server library  desktop/                Electron client (macOS-first release path)  mobile/                 Expo/React Native client  extension/              Chrome extensionpackages/                 Shared @genfeedai/* packagesdocker/                   Community and hosted image definitions

The public API is REST/OpenAPI. GraphQL appears only in outbound integrations such as Shopify.

The stack is declared, not debated per-PR. Replacing an item requires an accepted ADR before code lands (see GOVERNANCE.md).

LayerChoiceWhy
Runtime + PMBun + TurborepoOne toolchain for install, scripts, tests, and bundling
WebNext.js 16 + React 19App Router, RSC, and the same client for SaaS, Community, and Desktop
APINestJS 11DI, guards, and tenancy/auth enforcement across services
DataPrisma 7 + PostgreSQLOne schema, typed queries, migrations shipped with every release
QueuesRedis + BullMQGeneration, publishing, and scheduling are background work
AuthBetter AuthSelf-hostable, org-aware, no vendor account required for Community
QualityBiome, Vitest, PlaywrightFormat+lint in one pass; colocated unit tests; E2E tiers per distribution
DistributionDocker Compose + GHCRChecksummed bundle pinned to an image

More: Architecture · Deployment Modes · Execution Boundaries · Agent Surface.

Contributing

Contributions are voluntary and unpaid. Genfeed has no paid contribution program; see the contribution policy.

Audience order for this repository is self-hosters, then agent contributors, then human contributors. Development is supported on macOS and Linux (Windows via WSL2). Prerequisites: Node 26, Bun, Docker with Compose v2, a C/C++ toolchain plus python3 (sudo apt-get install -y build-essential python3 on Debian/Ubuntu, xcode-select --install on macOS), and systemd on Linux for dev:setup. Details are in CONTRIBUTING.md.

bash
bun install && cp .env.example .env.localbun run env:sync localdocker compose -f docker/local/docker-compose.yml up -d postgres redisbun run dev:setup                  # once per machinebun run dev:backend:min            # then, in a second terminal:bun run dev:web                    # → https://app.genfeed.localhost/

Portless HTTPS is the default contributor dev path. Fixed-port dev:debug* commands remain an optional debugging path when Portless cannot be used. Everything else — issue forms and EARS criteria, the PR contract (squash + conventional title + linked issue), the CLA (once per GitHub account per CLA version), agent-authored PR disclosure, and focused verification — is in CONTRIBUTING.md.

Governance is one maintainer plus an AI review pipeline: GOVERNANCE.md. Help and questions: SUPPORT.md. Security reports follow SECURITY.md, never a public issue.

Licence and trademark

Independently published packages and skills may declare their own license in their package metadata.

Links

Repository docs (docs/ in this tree) are for contributors and self-hosters: self-hosting, deployment modes, architecture, agent surface, and native referral credits. docs.genfeed.ai is the product and API documentation for people using Genfeed. Each side links the other; neither duplicates the other.

來源:README.md,提交 c5333ee

工具

0
該伺服器需要登入,因此 SourceWeft 無法在沒有帳號的情況下讀取其工具,也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

1
  1. v0.2.13-icons.1最新Oct 21, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分