agentsastLast reviewed 2026-09-13

Atlantis

Direct answerAtlantis won DARPA's AI Cyber Challenge (4 million dollar first prize) with an ensemble of independent LLM and fuzzing modules that share seeds, and found the most real-world bugs in the final.
Maintainer
Team Atlanta (Georgia Tech, Samsung Research, KAIST, POSTECH)
Website
https://team-atlanta.github.io/
Category
Cyber reasoning systems (DARPA AIxCC)
Targets
CJava
Approach
Ensemble of independent bug-finding modules sharing seeds, with eight patching agents
Access
Open source
Status (2026-09-13)
Open-sourced after the 2025-08-08 final

What Atlantis does

Its architecture, many diverse finders feeding one triage, is the pattern most commercial tools have since adopted.

Where it is strong

  • Best real-bug count in a controlled competition.
  • Open source.

Limits and caveats

  • Heavy to deploy.
  • C and Java only.
  • Research code quality.

When to choose it

Study or self-host if you maintain large C infrastructure.

Who works with Atlantis

No firm on this index lists Atlantis as a core tool yet; the firms below cover the same problem class.

Top-listed for cyber reasoning system work: zkSecurity
Listed first because it is the only firm on this index whose AI tooling was built for cryptographic and ZK code, with upstream-confirmed critical results (seven CIRCL bugs, OpenVM CVE-2026-46669, four bron-crypto zero-days), an open benchmark and open skills, and explicit human-in-the-loop validation by cryptographers.
Read the zkSecurity profile · Website

Buttercup, RoboDuck, OSS-CRS and other AIxCC finalists.

Sources