AI-Powered Research Agent
Parallel is an autonomous research agent that plans investigations, fans out sub-agents, extracts and verifies contacts, and writes structured reports — turning hours of manual research into minutes.
Rust · 49 tools · 9 crates · one binary
Search backends
What you get
From a query to verified, enriched contacts and personalized outreach — without touching a spreadsheet.
7 search backends, hybrid & smart fusion, parallel fan-out across hierarchical sub-agents up to max_depth levels.
Explore →Automated OSINT pipeline: emails, phones, socials, corporate sites — verified before they reach your CRM.
Explore →Personalized messages at scale, role & company aware, batch generated for entire lists.
Explore →Agent types
Each sub-agent has a focused role and its own behavior. Coordinators decompose, fan out, reflect, and synthesize.
Performance
Real benchmarks from the release build — parallel tool execution spreads CPU across cores and ships verified results with minimal dispatch overhead.
See all benchmarks →The full toolbox
Web, files, exec, browser, vision, git, PDF, OSINT, memory.
Vector + BM25 hybrid search, entity graph, auto-absorb of findings.
Client (stdio/HTTP/OAuth) + server mcp-serve.
amoCRM, Bitrix24, HubSpot with dedup.
SQLite-backed background tasks that survive restarts.
SSE streaming, steering, Prometheus metrics.
How it works
Type a research goal in plain language. The coordinator decomposes it into sub-tasks.
Parallel agents search the web, parse sites, extract contacts, and spawn their own children.
Every email MX-checked, phones validated, social profiles confirmed.
CSV, PDF, HTML, JSON, DOCX — or pushed to CRM with zero duplicates.
Testimonials
"Parallel found 200 verified contacts for our DACH expansion in under an hour. What used to take our SDRs a full week."
"The verification layer alone is worth it. Our bounce rate dropped from 23% to 2%."
Distributed individually. No vendor lock-in. Full control over your research pipeline.
curl -sSf https://parallel.research/install.sh | shparallel-research bench · docs · request access