Research and report agents for building multi-agent systems
Agents that search, read many sources and return a cited answer or report. Of the 102 tools on our building multi-agent systems page, 8 fit this narrower job. By pricing: 6 open source, 1 free or freemium, 1 paid, usage-based or enterprise. The most-starred open repos here are DeepCode (16,756 stars), AutoDev (4,561 stars), Paper2Agent (3,892 stars). Most come from the coding (2), research (2), security & governance (2) categories.
Updated
DeepCode
Open agentic coding system that turns papers and specs into code with multi-agent orchestration.
Added
AutoDev
Multi-agent development platform built on Kotlin Multiplatform for research, coding, review and data queries across IntelliJ, VS Code, CLI and more.
Added
Paper2Agent
Multi-agent system that turns a research paper and its code into a working MCP server and agent skills you can query and run.
Added
Pentest AI Agents
Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections.
Added
open-kritt
A self-hosted AI security research tool that orchestrates agents to hunt for vulnerabilities in a codebase and then validate and rank what they find; managed scans are also offered.
Added
Grok Bot Jev Router
Grok Bot Jev Router is an open-source Python reference router that puts TypeSafe Jev in front of Grok Bot as a cheap decision layer. Before expensive research, browser, retry or subagent work, Jev classifies the request and returns an explicit action such as reuse a cached result, stop a failing retry, cap research, run a deterministic step, or ask a human. It starts in shadow mode that only logs decisions, has an active mode for a Grok Bot skill that honors them, and includes a kill switch. It never sends, pays or deletes anything itself.
Added
Crewdle
Hire autonomous agents and teams for support, sales, bookkeeping and research, paid per task.
Added
Google Deep Review
Google Research's multi-agent system that checks research papers, design docs, and legal or financial documents for logical gaps and unsupported claims.
Added
GitHub repos (6)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| DeepCode ↗ | 16,756 | MIT | 2026-10-26 |
| AutoDev ↗ | 4,561 | Mozilla Public License 2.0 | 2026-09-25 |
| Paper2Agent ↗ | 3,892 | MIT | 2026-09-17 |
| Pentest AI Agents ↗ | 2,377 | — | — |
| open-kritt ↗ | 2,353 | — | 2026-10-26 |
| Grok Bot Jev Router ↗ | 119 | — | 2026-09-28 |
6 repos. Stars and licence come from each repo, checked when the listing was last verified.
FAQ
What are the best AI tools for building multi-agent systems focused on research and reports?
We list 8. The first three by GitHub stars and featured status are DeepCode: Open agentic coding system that turns papers and specs into code with multi-agent orchestration.; AutoDev: Multi-agent development platform built on Kotlin Multiplatform for research, coding, review and data queries across IntelliJ, VS Code, CLI and more.; Paper2Agent: Multi-agent system that turns a research paper and its code into a working MCP server and agent skills you can query and run.
Are there free or open-source options?
Yes: 6 open source, 1 free or freemium, 1 paid, usage-based or enterprise. Pricing is as each maker states it.
More from building multi-agent systems
Tools are grouped by what each says it does. Missing one? Submit it free.