elder-plinius/T3MP3ST

autonomous red teaming platform; multi-agent offensive-security meta-harness

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 41 seconds ago
Added to GitGenius on September 11th, 2026
Created on July 2nd, 2026
Open Issues & Pull Requests: 5 (+0)
GitHub issues: Enabled
Number of forks: 1,288
Total Stargazers: 6,114 (+0)
Total Subscribers: 60 (+0)

Repository Insights (GitGenius)

Most active contributors

Sign in to see contributor activity.

Related repositories by overlapping contributors

No overlapping-contributor repos identified yet.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 4
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 14 days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • enhancement (5)
  • bug (2)
  • documentation (2)
  • hitl (1)
  • question (1)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

t3mp3st is an autonomous red teaming platform that orchestrates multiple AI agents to conduct offensive security assessments.

The tool addresses the challenge of scaling security testing by automating the coordination of multiple specialized agents working together on red team objectives. Rather than requiring manual orchestration of individual security tools and human testers, t3mp3st functions as a meta-harness that enables agents to operate autonomously while maintaining coherent attack strategies. The multi-agent architecture allows different agents to specialize in distinct offensive techniques and share findings, creating a more comprehensive and efficient assessment than sequential manual testing.

Organizations evaluating t3mp3st should consider it if they need to automate red team workflows and can integrate autonomous agents into their security testing processes. The project suits teams that want to move beyond point-tool security scanning toward coordinated, intelligent offensive assessments. This approach works best in environments where security teams can define clear red team objectives and allow agents to pursue them with minimal human intervention.

The project shows active development with regular commits addressing core functionality and agent coordination. Work spans implementation of the multi-agent orchestration layer, integration of offensive security capabilities, and refinement of how agents communicate and share attack context. The codebase demonstrates ongoing attention to the meta-harness architecture that ties agents together into coherent campaigns.