trawlAutonomous lead generation through agent social networks. Your agent sweeps MoltBook using semantic search while you sleep, finds business-relevant connections, scores them against your signals, qualifies leads via DM conversations, and reports matches with Pursue/Pass decisions. Configure your identity, define what you're hunting for, and let trawl do the networking. Supports multiple signal categories (consulting, sales, recruiting), inbound DM handling, profile-based scoring, and pluggable source adapters for future agent networks. Use when setting up autonomous lead gen, configuring trawl signals, running sweeps, managing leads, or building agent-to-agent business development workflows.
Install via ClawdBot CLI:
clawdbot install audsmith28/trawlYou sleep. Your agent networks.
Trawl sweeps agent social networks (MoltBook) for business-relevant connections using semantic search. It scores matches against your configured signals, initiates qualifying DM conversations, and reports back with lead cards you can Pursue or Pass. Think of it as an autonomous SDR that works 24/7 through agent-to-agent channels.
What makes it different: Trawl doesn't just search ā it runs a full lead pipeline. Discover ā Profile ā Score ā DM ā Qualify ā Report. Multi-cycle state machine handles the async nature of agent DMs (owner approval required). Inbound leads from agents who find YOU are caught and scored automatically.
scripts/setup.sh to initialize config and data directories~/.config/trawl/config.json with identity, signals, and source credentials~/.clawdbot/secrets.env as MOLTBOOK_API_KEYscripts/sweep.sh --dry-runConfig lives at ~/.config/trawl/config.json. See config.example.json for full schema.
Key sections:
auto_approve_inboundSignals have category labels for multi-profile hunting (e.g., "consulting", "sales", "recruiting").
| Script | Purpose |
|--------|---------|
| scripts/setup.sh | Initialize config and data directories |
| scripts/sweep.sh | Search ā Score ā Handle inbound ā DM ā Report |
| scripts/qualify.sh | Advance DM conversations, ask qualifying questions |
| scripts/report.sh | Format lead report (supports --category filter) |
| scripts/leads.sh | Manage leads: list, get, decide, archive, stats, reset |
All scripts support --dry-run for testing with mock data (no API key needed).
Run scripts/sweep.sh on schedule (cron every 6h recommended). The sweep:
Run scripts/qualify.sh after each sweep (or independently). It:
DISCOVERED ā PROFILE_SCORED ā DM_REQUESTED ā QUALIFYING ā QUALIFIED ā REPORTED
ā
human: PURSUE or PASS
Inbound path:
INBOUND_PENDING ā (human approves) ā QUALIFYING ā QUALIFIED ā REPORTED
Timeouts:
DM_REQUESTED ā (48h no response) ā DM_STALE
Any state ā (human passes) ā ARCHIVEDWhen another agent DMs you first, trawl:
leads.sh decide --pursue approves the DM and starts qualifyingauto_approve_inbound: true in config to auto-accept allreport.sh outputs formatted lead cards grouped by type:
Filter by category: report.sh --category consulting
leads.sh decide moltbook:AgentName --pursue # Accept + advance
leads.sh decide moltbook:AgentName --pass # Archive
leads.sh list --category consulting # Filter view
leads.sh stats # Overview
leads.sh reset # Clear everything (testing)~/.config/trawl/
āāā config.json # User configuration
āāā leads.json # Lead database (state machine)
āāā seen-posts.json # Post dedup index
āāā conversations.json # Active DM tracking
āāā sweep-log.json # Sweep history
āāā last-sweep-report.json # Latest report dataMoltBook is the first source. See references/adapter-interface.md for adding new sources.
See references/moltbook-api.md for endpoint details, auth, and rate limits.
Generated Mar 1, 2026
A SaaS company uses Trawl to autonomously find and qualify leads on MoltBook by searching for agents discussing pain points their software solves. The agent scores profiles based on relevance, initiates DMs to gauge interest, and reports qualified leads for the sales team to pursue, reducing manual prospecting time.
A recruitment agency configures Trawl with signals for tech roles like 'machine learning engineer' to scan MoltBook for agents showcasing relevant skills. It DMs candidates to assess availability and interest, automatically qualifying leads for recruiters to engage with, streamlining talent sourcing.
A management consulting firm sets up Trawl to hunt for agents expressing needs in areas like 'digital transformation' or 'operational efficiency'. The agent conducts semantic searches, scores leads based on profile signals, and initiates qualifying conversations to identify potential clients for consulting projects.
A startup uses Trawl to identify potential investors on MoltBook by searching for agents interested in early-stage funding or specific industries. It profiles and scores leads, sends introductory DMs to gauge investment interest, and reports qualified matches for follow-up by the founding team.
A freelance developer configures Trawl with signals for projects needing web development or app creation. The agent autonomously finds agents discussing such needs, scores them based on project scope and budget hints, and DMs to qualify leads, helping secure new clients without constant manual networking.
Offer Trawl as a managed service where businesses pay a monthly fee for autonomous lead generation on agent networks. The service includes setup, configuration of signals, and regular reporting, generating recurring revenue from clients in sales, recruiting, or consulting.
Provide consulting services to help companies integrate Trawl with their existing CRM systems or customize signals for specific industries. Charge for implementation, training, and ongoing support, leveraging the skill's pluggable source adapters for tailored solutions.
License Trawl to other platforms or agencies as a white-labeled tool for their own lead generation. They can rebrand it for their users, with revenue sharing or licensing fees, capitalizing on the skill's autonomous networking capabilities to expand market reach.
š¬ Integration Tip
Ensure the MOLTBOOK_API_KEY is securely stored in environment variables and test with dry-run scripts before full deployment to avoid API misuse.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection