AI GROWTH AGENT · RUNNING LOCALLY

Grow on X
while you sleep.

X-Autopilot is a fully local AI agent that opens a real Chrome browser, logs into your Twitter/X account, and engages with your target audience 24/7 — liking, replying, following — written entirely in your voice, powered by Claude or GPT-4.

40+
Replies / day
45+
Likes / day
10+
Follows / day
4
DMs / day
100%
Your voice
0
Cloud servers
01 — OVERVIEW

What Is X-Autopilot?

X-Autopilot is a desktop AI agent — it runs entirely on your Mac or Windows computer. No monthly subscription, no cloud server, no data leaving your machine. It opens a real Google Chrome browser, navigates Twitter just like a human would, and autonomously engages with your audience throughout the day.

🧠
AI CORE

Writes In Your Voice

Powered by Claude (Anthropic) or GPT-4 (OpenAI). The AI knows your niche, personality, products, and phrases you'd never say — every reply sounds like you wrote it.

👻
STEALTH

Undetectable Automation

Uses a real Chrome browser with GPU/CPU fingerprint spoofing, randomised typing speed, natural mouse trajectories, and human scroll physics. Twitter sees a real user.

🎯
TARGETING

Smart Account Targeting

Engages with your hand-picked target accounts, trending hashtags, and home feed. Automatically discovers new relevant accounts to follow and engage with.

📊
DASHBOARD

Live Web Dashboard

Monitor everything at localhost:5001 — live action log, stats, follower growth chart, settings, and controls. Works in any browser.

🔒
PRIVACY

100% Local & Private

Your API keys, Twitter session, and activity data never leave your machine. No accounts to create, no cloud sync, no external servers involved whatsoever.

EASE OF USE

Zero Coding Required

Double-click to install, double-click to start. Configure everything through the visual dashboard. No terminal knowledge needed after the one-time setup.

02 — REQUIREMENTS

What You Need

SOFTWARE

Required Software

Google Chrome REQUIRED
Python 3.9+ REQUIRED
Anthropic API Key ONE OF THESE
OpenAI API Key ONE OF THESE
HARDWARE / OS

Supported Systems

🍎 macOS 12+ SUPPORTED
🪟 Windows 10 / 11 SUPPORTED
RAM 4GB minimum
Disk Space ~800MB (venv)
Node.js is not required. The dashboard is pre-built and served by Python. You only need Python + Chrome to run X-Autopilot.
03 — INSTALLATION

Installation

🍎 MACOS
🪟 WINDOWS
1

Verify Python is installed

Press ⌘ Space, type Terminal, press Enter. Then run:

python3 --version

You should see Python 3.x.x. If not, download from python.org/downloads — install the latest 3.x release.

2

Unzip X-Autopilot

Double-click x-autopilot.zip to extract it. Move the folder somewhere permanent — your Desktop or Documents folder works well. Don't run it from inside the ZIP.

3

Run Setup (one time only)

Inside the folder, find 2. Setup.command and double-click it.

First time on Mac: macOS may block it. Right-click → Open → click Open in the popup. After this once, it runs normally on double-click.

A terminal window opens and automatically installs all dependencies. This takes 2–4 minutes. When it says Setup complete, close the terminal.

4

Start the agent

Double-click 4. Run Agent.app. The dashboard opens in its own window at localhost:5001 — no browser tabs, no clutter. On Windows, double-click start.bat instead.

First time on Mac: macOS may block it. Right-click 4. Run Agent.app → Open → click Open in the popup. You only need to do this once.
5

Add your credentials

Go to localhost:5001 → Settings → Account & API Keys and enter your Twitter username and Anthropic/OpenAI key. Hit Save. Done.

1

Install Python

Go to python.org/downloads and download the latest Python 3.x installer. Run it and check the box "Add Python to PATH" — this is critical or nothing will work.

2

Extract the ZIP

Right-click x-autopilot.zipExtract All. Put the folder on your Desktop or Documents. Don't run from inside a ZIP.

3

Run setup.bat

Double-click setup.bat. A black console window installs everything automatically.

Windows Defender may show a warning. Click More info → Run anyway. The script is safe — it only installs Python packages.
4

Start with start.bat

Double-click start.bat every time you want to run X-Autopilot. Your browser will open the dashboard automatically.

5

Add credentials via dashboard

Open localhost:5001 → Settings → Account & API Keys in your browser and enter your details.

04 — CREDENTIALS

API Keys Setup

X-Autopilot needs an AI API key to generate replies, analyse tweets, and write in your voice. You need at least one. Both can be added as a fallback.

ANTHROPIC · RECOMMENDED

Claude API

BEST QUALITY

Claude writes the most natural, contextual replies. Best at matching personality and avoiding robotic phrasing. Strongly recommended over OpenAI for this use case.

HOW TO GET YOUR KEY
1 · Go to console.anthropic.com
2 · Sign up or log in
3 · Click API Keys → Create Key
4 · Copy the key — starts with sk-ant-
Cost: ~$3–8 / month at 40 replies/day · Free trial credits available
OPENAI · OPTIONAL

GPT-4 API

FALLBACK

X-Autopilot can use GPT-4o or GPT-4o-mini as a fallback when Claude is unavailable, or as your primary provider if you prefer OpenAI.

HOW TO GET YOUR KEY
1 · Go to platform.openai.com
2 · Sign up or log in
3 · Click API Keys → Create new secret key
4 · Copy the key — starts with sk-proj-
Cost: ~$1–5 / month using gpt-4o-mini · Pay-as-you-go
Enter your keys in the dashboard at Settings → Account & API Keys and click Save. Keys are stored locally in your .env file and never transmitted anywhere.
DASHBOARD · SETTINGS TAB
localhost:5001
OVERVIEW
ACTIVITY
SETTINGS
GROWTH
ACCOUNT & API KEYS
TWITTER USERNAME
your_handle_here
ANTHROPIC API KEY
sk-ant-••••••••••••••••••••
SAVED
OPENAI API KEY (FALLBACK)
leave blank if not using OpenAI
SAVE CREDENTIALS
05 — FIRST RUN

First Run & Login

1

Launch the agent

Double-click 4. Run Agent.app (Mac) or start.bat (Windows). The dashboard opens in its own dedicated window at localhost:5001 — no address bar, no browser tabs.

2

Log into Twitter in the Chrome window

Chrome opens Twitter's login page. Sign in with your account username and password — exactly as you normally would. Complete any 2FA or phone verification Twitter asks for.

This login is one-time only. X-Autopilot saves your session so future launches don't require logging in again — unless Twitter expires your session (usually after 30+ days of inactivity).
3

Confirm in the terminal

Once you're on your Twitter home feed, switch back to the terminal window and press ENTER. The agent confirms the session and begins operating.

4

Watch it go

A floating status bar appears in the Chrome window showing what the agent is doing in real-time. The dashboard at localhost:5001 shows live stats and action logs.

5

To stop the agent

On Mac: close the dashboard window or press Cmd+Q — the agent stops automatically. You can also double-click 4. Run Agent.app again while it's running and click Quit. On Windows: close the terminal window or use the Quit button in the dashboard.

06 — DASHBOARD

Dashboard · Overview Tab

Open http://localhost:5001 in any browser. The Overview tab is your mission control.

localhost:5001 — X-Autopilot Dashboard
OVERVIEW
ACTIVITY
SETTINGS
GROWTH
REPLIES TODAY
23
↑ 40 target
LIKES TODAY
31
↑ 45 target
NEW FOLLOWERS
+7
since yesterday
WIDGETWHAT IT SHOWS
Replies TodayNumber of replies posted so far vs. your daily target
Likes TodayLikes given today — counts toward daily limit to avoid rate limiting
Follows TodayNew accounts followed. Kept low (10/day) to avoid Twitter penalties
DMs SentDirect messages sent. Only 4/day to avoid spam flags
New FollowersNet new followers gained vs. yesterday's count
Agent StatusWhat the agent is doing right now — liking, replying, sleeping, etc.
Pause ButtonPauses the agent after its current action. Click again to resume.
Quit ButtonCleanly stops the agent. All progress is saved.
06b — DASHBOARD

Dashboard · Activity Tab

Every single action the agent takes is logged here with timestamp, action type, target tweet/user, and whether it succeeded.

RECENT ACTIVITY
11:42 PM ↩ REPLY Replied to @levelsio — "The distribution insight here is underrated…" OK
11:39 PM ♥ LIKE Liked tweet by @marc_louvion about pricing pages OK
11:35 PM + FOLLOW Followed @indie_builder_xyz · 840 followers OK
11:31 PM ◉ DM DM sent to @small_saas_founder after 3 interactions OK
ACTION TYPEICONCOLOURWHAT IT MEANS
REPLYBlueAI-written reply posted to a tweet
LIKEPinkTweet liked
FOLLOW+PurpleAccount followed
UNFOLLOWGreyAccount unfollowed (non-followers after 14 days)
DMOrangeDirect message sent
TWEETGreenOriginal tweet posted (after your approval)
QUEUEDYellowAI-generated tweet waiting for your approval in the dashboard
06c — DASHBOARD

Dashboard · Settings Tab

The Settings tab lets you change everything without touching config.yaml. Changes save instantly and take effect on the next agent action.

SECTIONSETTINGS AVAILABLE
Account & API KeysTwitter username, Anthropic API key, OpenAI API key (fallback)
Voice & PersonaNiche, personality, products, product URLs, never-say phrases
Daily TargetsReplies, likes, follows, DMs, retweets per day
Posting ScheduleActive hours start/end, tweet times
Target AccountsAdd/remove Twitter accounts to engage with
DiscoveryHashtags, home feed scanning, max tweets scanned
SafetyMax actions per hour, pause between sessions, rate limit behaviour
AutonomyAutonomy level (0–100%), require tweet approval toggle
06d — DASHBOARD

Dashboard · Growth Tab

The Growth tab shows your follower count over time as a chart. Data is recorded at the end of each active day.

Growth data appears after the first full day of running. Before that, the chart shows sample data so you can preview the layout. Each data point represents one day's end follower count, so you can track your trajectory week by week.
FOLLOWER GROWTH — SAMPLE PREVIEW
D1
07 — AUTOMATION

Actions Explained

ACTIONHOW IT WORKSDAILY LIMITTRIGGER
↩ REPLY AI reads the tweet, generates a reply in your voice, opens the reply box and types it with human-like speed and occasional typos that get corrected. 40 / day Target accounts, hashtag feed, home feed
♥ LIKE Clicks the like button on relevant tweets from your targets and home feed. Helps with visibility and signals engagement before following. 45 / day Target profiles, home feed, hashtag results
+ FOLLOW Follows accounts that match your niche and have engaged with relevant content. Focuses on smaller accounts most likely to follow back. 10 / day Post engagement, hashtag discovery, mentions
◉ DM Sends personalised DMs to small accounts after several interactions. AI writes a context-aware opening message — not a generic pitch. 4 / day After 2+ likes/replies to same account
◈ TWEET AI generates original tweet drafts aligned with your content strategy. By default, these appear in the dashboard for your approval before posting. 4 / day Scheduled tweet times in config.yaml
− UNFOLLOW Automatically unfollows accounts that didn't follow back after 14 days, keeping your following/follower ratio healthy. Auto 14 days after follow, if not followed back
🔔 NOTIFS Checks notifications, reads the full conversation thread (scrolling up to see original post + your reply + their response), then decides how to reply again. 3 / session Notification tab — replies, mentions, DMs
↻ RETWEET Retweets highly relevant content when the AI's relevance score is above threshold. Kept very low to maintain authenticity. 2 / day High-scoring relevant tweets only
⊛ PRODUCT When a tweet's topic matches your product's keywords (e.g. "invoicing", "icon pack"), the reply weaves in a natural product mention — value add first, then a conversational "I built something for this" with your URL. 2 / day Keyword match on tweet text vs. product trigger list
Product mentions are subtle by design. The AI is instructed to add genuine value to the conversation first. The product link comes last, framed like a builder sharing their own tool — never "check out" or "try this". Configure keywords and daily limit under promotions: in config.yaml.
08 — STRATEGY
+

Tiered Engagement Strategy

X-Autopilot treats accounts differently based on their follower count. This maximises follow-backs from small creators while gaining visibility from large ones.

SMALL · 0–1K

Relationship Mode

Your future loyal fans. Highest follow-back rate.

→ Warm, conversational replies
→ Asks one genuine question
→ DM follow-up enabled
→ Likes older posts from profile
→ Welcome DM on new follows
PEER · 1K–10K

Networking Mode

Your collaborators and cross-promoters.

→ Opinionated, adds depth
→ Treats them as an equal
→ DM follow-up enabled
→ Builds mutual respect tone
→ Engages across multiple posts
BIG · 10K+

Visibility Mode

Exposure to their large audiences.

→ Sharp, specific, insightful
→ Replies within 15 min of post
→ No DMs (verified accounts)
→ Aims for top-of-thread position
→ Contrarian or additive takes
09 — SCHEDULE

Sessions & Daily Schedule

X-Autopilot runs in intelligent sessions with natural breaks — not continuously. This looks human and stays under Twitter's rate limits.

09:00 AM — WAKE UP
Agent activates. Checks notifications from overnight. Replies to any mentions. Scans home feed for first-of-morning engagement opportunities.
09:30 AM — MORNING SESSION
First full engagement session. Discovers new target accounts from hashtags (checks bio + follower count for fit). Visits target profiles, likes 6–10 recent posts, posts 4–7 replies. Follows 2–3 new accounts.
10:30–12:00 PM — NATURAL BREAK
Light activity. Occasional idle scrolling of home feed to maintain session warmth. No heavy engagement. Random 8-minute scroll intervals.
12:00 PM — MIDDAY SESSION
Hashtag scan + DMs. Searches configured hashtags for high-engagement posts to reply to. Sends DMs to warmed-up small accounts. Processes any new notifications.
2:00–5:00 PM — AFTERNOON BREAK
Profile like session. Visits 2 target profiles and likes 3–6 older posts from each — a subtle signal that gets noticed by creators who check their analytics.
6:00 PM — EVENING SESSION
Prime time. Biggest accounts post most in the evening. The agent watches target feeds closely and replies to fresh posts fast — within 15 minutes for big accounts to maximise visibility.
8:00–10:00 PM — LATE SESSION
Follow-up engagement. Checks notification replies to the agent's own earlier comments. Reads full thread context before replying again. Processes any new followers with a welcome interaction.
11:00 PM — SLEEP
Agent rests. All daily counters reset at midnight. No activity until 9am the following morning.
Skip Break: When the agent is resting between sessions, a yellow ⏩ Skip button appears in the browser status bar. Click it to jump immediately to the next session without waiting.
10 — BROWSER OVERLAY

Browser Status Overlay

A floating status bar appears at the top of the Chrome window while X-Autopilot runs. It shows the current status and gives you quick controls without opening the dashboard.

X-AUTOPILOT ● Replying to @levelsio…
[Twitter/X page content appears here]
BUTTONWHEN VISIBLEWHAT IT DOES
⏩ SKIPDuring breaks and sleep periodsImmediately ends the current rest period and starts the next engagement session
⏸ PAUSEAlways visible during active sessionPauses after the current action completes. Click again (▶ RESUME) to continue.
✕ QUITAlways visibleSends a clean shutdown signal. Agent finishes its current action, saves all data, then stops.
11 — SAFETY

Safety & Rate Limits

X-Autopilot has multiple layers of safety built in to protect your account. These run automatically — you don't need to do anything.

DAILY CAPS

Hard Daily Limits

Repliesmax 40 / day
Likesmax 45 / day
Followsmax 10 / day
DMsmax 4 / day
Actions / hourmax 12 / hour
HUMAN SIMULATION

Anti-Detection Layers

→ Real Chrome with GPU/CPU spoofing
→ Randomised typing speed (25–90ms/char)
→ Natural mouse trajectories with drift
→ Hover dwell before every click
→ Occasional typos that get corrected
→ Trackpad-style scroll physics
→ 15–90s randomised delay between actions
→ Natural breaks and idle scrolling
Rate limit detected: If Twitter responds with a rate limit signal, X-Autopilot automatically pauses for 90 minutes and then resumes. This is handled entirely without your input.
12 — CONFIGURATION

Voice & Persona Setup

This is the most important configuration. The more specific you are, the more your replies will sound like you and not a generic AI.

voice: # Your niche — be specific, comma-separated niche: indie hacker, design, solopreneurship, SaaS # 3-4 adjectives that describe your writing style personality: thoughtful, analytical, dry humor # Your product(s) — used for subtle contextual mentions product: YourProduct, YourOtherProduct product_url: https://yourproduct.com # Phrases the AI will NEVER use — kills the "AI voice" never_say: - consistency is key - the grind never stops - let's goooo - hustle hard - crush it - game changer - absolutely - certainly
The never_say list is your secret weapon. Add any phrase that sounds corporate, generic, or unlike you. The more you add, the more authentic the output becomes.
13 — TARGETING

Target Accounts — Auto-Discovered

No hardcoded accounts needed. X-Autopilot scans your niche hashtags each morning, visits candidate profiles, checks their bio and recent tweets for relevance, and adds qualifying accounts automatically — sorted into the correct tier by follower count.

# No manual list required — agent discovers targets automatically target_accounts: [] targets: auto_add_enabled: true # Auto-discover new targets from hashtags auto_add_max_per_day: 6 # Max new targets added per day auto_add_min_followers: 0 # Minimum followers to qualify follow_from_mentions_enabled: true follow_from_home_enabled: true
How discovery works: Every morning session, the agent searches 2 of your configured hashtags, collects authors, visits each profile, reads their bio + recent tweets, and runs a relevance check against your voice/niche profile. Accounts that pass are added to data/targets.json with the correct tier (small / peer / big) based on follower count. You never need to maintain a manual list.
First run: On the very first morning session the target list is empty, so the agent will spend a few minutes discovering accounts before starting engagement. After that, the list grows on its own daily.
14 — FULL REFERENCE

Full Config Reference

Every setting in config.yaml — explained. You can edit this file directly or use the Settings tab in the dashboard.

POSTING
ENGAGEMENT
DISCOVERY
SAFETY
NOTIFICATIONS
KEYDEFAULTDESCRIPTION
tweets_per_day4How many original tweets the AI generates per day
require_approvaltrueIf true, tweets queue in dashboard for your review. Set false for full auto-posting.
tweet_times09:30, 19:00Times the agent attempts to post original tweets
active_hours_start09:00Agent wakes up at this time each day
active_hours_end23:00Agent sleeps at this time each day
KEYDEFAULTDESCRIPTION
daily_replies40Maximum replies per day across all sessions
daily_likes45Maximum likes per day
daily_follows10Maximum new follows per day
daily_dms4Maximum DMs per day — keep low to avoid spam flags
daily_retweets2Maximum retweets per day
min_delay_seconds15Minimum wait between actions (seconds)
max_delay_seconds90Maximum wait between actions (seconds)
KEYDEFAULTDESCRIPTION
hashtagsbuildinpublic…Hashtags to scan for relevant tweets to reply to
reply_from_hashtagstrueWhether to find and reply to tweets via hashtag search
reply_from_home_feedtrueWhether to reply to tweets from your home feed
max_hashtag_replies_per_session5Max replies from hashtag results in one session
max_home_replies_per_session8Max replies from home feed in one session
max_hashtag_tweets_scanned60How many hashtag tweets to scan before picking the best ones
candidate_score_threshold0.15Minimum relevance score for a tweet to qualify for reply
use_embeddingstrueUse vector embeddings for semantic tweet relevance scoring
min_likes0Minimum likes a tweet must have to be engaged with
KEYDEFAULTDESCRIPTION
max_actions_per_hour12Hard cap on total actions in any 60-minute window
pause_between_sessions_minutes60Rest time between engagement sessions
unfollow_non_followers_after_days14Days before unfollowing accounts that haven't followed back
idle_scroll_enabledtrueScroll home feed during breaks to look human
idle_scroll_interval_minutes8How often to do an idle scroll during breaks
stop_on_rate_limittruePause if Twitter signals rate limiting
rate_limit_cooldown_minutes90How long to wait after a rate limit is detected
dynamic_pacingtrueAutomatically slow down if approaching daily limits early
KEYDEFAULTDESCRIPTION
reply_to_mentionstrueAutomatically reply to tweets that mention you
max_reply_notifications_per_session3Max notification replies processed per session
follow_welcome_enabledtrueSend a welcome interaction when someone follows you
max_follow_welcomes_per_session4Max welcome interactions per session
follow_welcome_like_min_posts3Min posts to like on a new follower's profile
15 — PRO TIPS

Pro Tips for Maximum Growth

TARGETING

Target the Sweet Spot

Add 20+ accounts in your exact niche. The best targets are creators with 500–5,000 followers who post regularly. They check their notifications obsessively and are most likely to engage back.

VOICE

Be Brutally Specific on Voice

Add at least 10 phrases to never_say. Include any word that sounds corporate or AI-generated. "Absolutely", "Certainly", "Great point" — all banned. The more you restrict, the better the output.

CONSISTENCY

Run It Every Day

Growth on X is compound. 30 days of 40 replies/day = 1,200 touch points. Those compound into follows, profile visits, and brand awareness. Running 3 days then stopping resets momentum.

TIMING

Prioritise Evening Active Hours

Set active hours to include 6pm–11pm local time. Your target accounts post in evenings. First replies on a fresh post from a big account get the most eyeballs — the agent watches for new posts.

CONTENT

Review Queued Tweets

With require_approval: true, the AI generates tweet drafts that appear in your dashboard. Review and edit these before approving — treat the AI as a first-draft writer. Your edits train your own eye for what works.

ANALYTICS

Track the Activity Log

The Activity tab shows everything the agent is doing. After a week, look for patterns — which reply styles get follow-backs? Which accounts respond? Use this to refine your targets and voice settings.

16 — FAQ
?

Frequently Asked Questions

Will Twitter ban my account?

X-Autopilot is designed to be undetectable at every layer. It uses a real Chrome browser with authentic GPU and CPU fingerprinting, randomised human typing speed (25–90ms per key), natural mouse curves with drift, hover dwell before clicks, trackpad-style scroll physics, and 15–90 second randomised delays between actions. Daily limits (40 replies, 45 likes, 10 follows) stay well within safe thresholds. No tool is 100% guaranteed, but X-Autopilot uses every known detection-avoidance technique. Use it at the recommended limits and you're in the safest possible zone.

Does my computer need to stay on the whole time?

Yes. X-Autopilot runs locally on your machine, so your computer and Chrome window need to stay open. You can minimise Chrome and lock your screen — the agent keeps running. If you close the terminal or Chrome, it stops. If you need 24/7 running without keeping your laptop on, you could run it on a cheap Windows VPS (like Hetzner or Contabo), but that's optional.

How much does the API cost per month?

Very little. At 40 replies/day × 30 days = 1,200 AI calls/month. At Claude's current pricing (claude-3-5-sonnet), that's roughly $3–8/month depending on reply length. Using GPT-4o-mini is even cheaper at $1–3/month. Both providers give free trial credits when you sign up. You can also reduce daily_replies to lower costs — even 15/day builds significant growth over a month.

Can I use my personal Twitter/X account?

Yes, and it's the recommended approach. X-Autopilot is designed for building a personal brand — your expertise, your niche, your products. It logs into your account via Chrome exactly as you would. One installation supports one account.

Will the AI replies sound real or robotic?

The whole system is designed around authenticity. The AI receives your niche, personality, writing style, forbidden phrases, product context, proof points, and the full text of the tweet it's replying to. Claude in particular is exceptional at avoiding "AI voice" — it produces specific, contextual, opinionated replies rather than generic affirmations. After setup, read the Activity log to see what it's posting. If anything sounds off, tighten your never_say list and personality description in config.yaml.

How do I stop it mid-session?

Mac: Close the dashboard window, press Cmd+Q, or double-click 4. Run Agent.app again and click Quit. All three stop the agent cleanly and close everything. Windows: Click the red ✕ QUIT button in the dashboard, or close the terminal window. All data is saved either way.

Does it post original tweets or just engage?

Both. By default (require_approval: true), the AI generates original tweet drafts that appear in the dashboard for your review and approval before posting. Replies to other tweets happen automatically without approval. You can set require_approval: false in config.yaml to let it post original tweets fully autonomously.

I closed the dashboard window — what do I do?

On Mac, closing the window intentionally stops the agent — just double-click 4. Run Agent.app to start it again. On Windows, double-click start.bat. Your Twitter session is saved in the Chrome profile so you won't need to log in again. All activity history is preserved.

Can I run this on a VPS or cloud server?

Technically yes — on a Windows VPS with Chrome installed and RDP access. It requires a visual desktop environment since Chrome runs as a visible window. Linux headless mode is not currently supported. A cheap Hetzner or Contabo Windows VPS (~$5–10/month) works well if you want 24/7 running without keeping your laptop on.

How long until I see follower growth?

Typically 2–4 weeks of consistent running. Growth is non-linear — the first week looks slow because you're building awareness. By week 3, the compounding effect kicks in as people start recognising your name from repeated quality comments. Accounts with a tight niche and specific voice tend to see faster results than broad accounts.

17 — TROUBLESHOOTING

Troubleshooting

PROBLEMLIKELY CAUSEFIX
Dashboard won't open at localhost:5001Server not started or port conflictRestart the agent. If port 5001 is in use, close other apps using it. Check terminal for error output.
"Python not found" on MacPython not installedDownload from python.org, install, re-run 2. Setup.command
2. Setup.command won't open on MacGatekeeper blocking unsigned scriptRight-click → Open → click Open. Only required once.
setup.bat blocked by Windows DefenderSmartScreen warningClick More info → Run anyway. The script only installs Python packages.
Browser stuck on X logo / black screenChrome restored previous session, React hydration failedNormal on first run or after a profile reset. The agent detects this automatically, clears the profile, and navigates to the login page.
Browser closes immediately on launchTwitter session expiredRestart — the browser will open the login page. Log in and press ENTER in the terminal.
Agent shows "outside active hours" and does nothingCurrent time outside configured hoursNormal behaviour. Adjust active_hours_start/end in config.yaml or Settings tab.
Replies sound generic or roboticVoice config too vagueAdd more entries to never_say. Make personality more specific. Add proof_bank examples.
API key error in activity logWrong or missing keyGo to Settings → Account & API Keys, re-enter your key, click Save.
Skip Break button not respondingOverlay not yet loadedWait 5 seconds and try again. The overlay refreshes every status update.
Rate limit warning appearsTwitter throttlingAutomatic — agent pauses 90 minutes then resumes. Reduce daily limits if recurring.
No actions after 30 minutesDaily limits already reachedCheck Overview tab — if counts hit limits, agent rests until midnight reset. Increase limits in config.yaml.
Chrome says "session expired, log in again"Twitter invalidated sessionNormal after ~30 days. Just log in again when prompted — session saves fresh.
"Module not found" error in terminalDependencies not installedRun 2. Setup.command/setup.bat again. It's safe to run multiple times.
Still stuck? Open the file data/agent.log inside the X-Autopilot folder. It has a detailed timestamped record of everything the agent did and any errors encountered.