AgentTube - ECGHuNZSECqTXabaLjkVrTEnguiNZLkKF1qi8oBGpump
The open-source AI agent that runs a YouTube channel end to end.
Join our telegram community: https://t.co/L4SzbqosOM
Research topics → write scripts → generate narration and visuals → assemble videos → optimize metadata → review → schedule → publish → learn from analytics and from what your audience says.
What's new on master
- v2.10.0 is now on master: DarkzSEO discoverability audits, controlled growth experiments, and outcome-aware channel operation are available together in the approval-first workflow.
What's new in v2.10.0
AgentTube now has a discoverability adapter layer. v2.10.0 connects the production pipeline to DarkzSEO without merging the projects or weakening human review, then adds the evidence needed to prove what packaging and strategy actually work:
- DarkzSEO Discoverability Preflight: send a canonical content package—not the private dashboard—through versioned GEO, AIO, AEO, and web-search checks after metadata and provenance are assembled.
- Reviewable evidence: persist stable rule IDs, severity, engine/schema identity, fingerprints, and operator decisions in SQLite. Keep a finding actionable or dismiss a false positive with a reason that carries into matching future audits.
- Safe local adapter boundary: invoke DarkzSEO through JSON-only stdin/stdout without a shell or inherited API secrets. Missing Python, timeouts, and schema drift stay explicit and non-blocking.
- Controlled Growth Experiments Studio: rotate only approved title/thumbnail arms, measure real interval evidence, restore the control, and require a separate decision before adopting a winner.
- Outcome & ROI Studio: align the operator with a measurable KPI, target window, budget, and available revenue/cost evidence without converting missing economics into false zeroes.
- Platform-ready foundation: audits already retain their target platform, providing the durable contract for planned TikTok and Instagram/Reels publishing and analytics adapters.
DarkzSEO is optional. Install DarkzSEO 1.4+ into Python or set DARKZSEO_PATH; when it is unavailable, AgentTube records the reason and keeps the existing approval workflow operational.
See the complete release history in CHANGELOG.md.
- Self-hosted: your credentials, media, and channel data stay under your control.
- Approval-first: nothing is scheduled until quality, rights, and human-review gates pass by default.
- Strategy-driven: give the Autonomous Channel Operator an objective, audience, pillars, cadence, and guardrails; it turns them into researched content plans and production runs.
- Provider-flexible: use Gemini, OpenAI, OpenRouter, Kimi, MiMo, GLM, or another OpenAI-compatible text endpoint, plus Seedance, MiniMax H3, Gemini Omni Flash, Kling, Wan, or local FFmpeg for video.
- Observable: follow persistent generation jobs, failures, review state, publishing, and local activation milestones from the dashboard.
Quick start
git clone https://github.com/darkzOGx/youtube-automation-agent.git
cd youtube-automation-agent
npm install
npm run walkthrough
npm start
Open http://localhost:3456. The walkthrough explains each provider choice, tests credentials, and guides YouTube authorization.
Already know what you are doing? npm run setup offers a shorter classic flow, and .env.example documents every setting.
Verify production readiness
Before activating autonomous production, open Production readiness in the dashboard and choose Run verified check. The gate makes small live text and narration requests, verifies access to the connected YouTube channel, creates and decodes a temporary MP4 containing audio and video, and validates every queued upload's metadata. It never creates or uploads a YouTube video, and temporary probe assets are deleted after the run.
AI image generation can incur a larger provider charge, so its live probe is a separate opt-in checkbox. Without that checkbox, image configuration is reported as verified, skipped, or using the built-in gradient fallback without making a paid image request.
AI video verification has its own Include paid video probe checkbox. When enabled, Lumen creates the provider's shortest supported test clip, records the external task and model, downloads and decodes the MP4, then removes the temporary asset. It never silently tries a second paid provider.
Results persist locally in SQLite with exact remediation steps. A recorded blocking failure stops autonomous generation and publishing until a later run passes; manual work remains available when readiness has never been checked or the last result is older than 24 hours.
Resume an interrupted production
Every generation stage writes a local SQLite checkpoint. If a provider times out or the application restarts, the dashboard shows the saved-stage count and the first incomplete stage. Choose Resume to continue from there, or select an earlier stage when you intentionally want to regenerate that stage and everything after it. Saved files are validated before reuse; missing artifacts are regenerated automatically.
Autonomous Operator runs preserve their research and editorial plan, so Resume run continues unfinished plan items instead of researching and generating completed videos again. Publishing remains fail-closed: if an upload may have reached YouTube but no video ID was returned, Lumen requires channel reconciliation before another upload attempt.
Repair one scene without starting over
Every production now keeps a durable scene manifest with its narration, visual prompt, timing, provider/task identity, asset origin, rights state, evidence links, and revision history. Open Scene Repair Studio inside Review Studio to edit a scene, change its order, lock a scene that already works, upload a licensed replacement asset, or regenerate only that scene.
Paid video regeneration always shows the provider and generated seconds and requires a separate confirmation. Uploaded assets require an explicit rights confirmation. Narration edits invalidate that scene's audio and factual review; live narration must be regenerated and any new factual claim must be reviewed against verified evidence before approval.
Narration is fail-closed. AgentTube records the TTS provider, model, external task when available, generation time, cost evidence, and failure reason for every scene. If narration is missing, simulated, stale, or failed, the production cannot be approved, scheduled, or published. Use Regenerate narration only to repair the audio without spending video-generation credits or replacing a visual.
An intentionally silent production requires a separate operator confirmation and a stored reason of at least 10 characters. The override remains visible in Review Studio, can be reversed, and is included in the narration revision history. Silence is never inferred from a failed provider call.
When the timeline is ready, Rebuild final video creates a new MP4 and scene-aware captions while preserving the previous final video path in the production record. Approval stays blocked while any scene is missing, generating, stale, failed, or waiting for rebuild. Approved or scheduled productions are locked against scene repair.
Repurpose an approved video into Shorts
Open Shorts Repurposing Studio inside Review Studio and choose Create 3 Short drafts. AgentTube selects self-contained windows from the durable scene timeline and preserves the exact source-scene IDs, start time, duration, rationale, title, description, tags, layout, and inherited review evidence for each candidate. Draft selection is local and does not call an AI provider.
Choose a blurred-canvas, center-crop, or stacked-focus layout, then render a real 9:16 MP4 with mobile-safe burned captions and a separate SRT file. The source video and narration are reused, so the default workflow does not spend new image, video, or TTS credits. Changing the layout invalidates the prior render and requires a fresh local render.
Every Short has its own approval and schedule. Scheduling remains blocked until the source production is approved, provenance is resolved, uploaded media rights are confirmed, every source scene is current, and the operator explicitly confirms the Short's privacy and publish time. Published Shorts retain their parent-production identity while their analytics use a separate Shorts baseline.
Review research and provenance
Every production has an Evidence desk inside Review Studio. Autonomous research carries exact YouTube source metadata into the production, while AI-generated scripts list the factual claims that need review. Add any official articles, datasets, asset licenses, or other evidence that the script needs, verify each source, and connect it to the claims it supports.
A claim can be approved only when it links to a verified source. Unsupported claims remain blocking, and an intentional waiver requires a reviewer note. Productions with no externally verifiable factual claims are marked as not requiring provenance review. The separate factual-review and media-rights attestations remain required before scheduling.
Use the altered or synthetic media control only when the video contains realistic content that requires YouTube disclosure. The selected value is preserved in the publishing queue and included in the YouTube upload request.