What problem it solves

Coordinated bug hunting is often gated by years of security practice, expensive tooling, and access to specialized workflows. The framework aims to make authorized reconnaissance, exploitation, and reporting more accessible while retaining explicit scope controls and reproducible evidence.

Key features

• Agent-led security workflow — Operators follow a reconnaissance-to-exploitation workflow through a browser War Room or CLI, using a connected coding agent or a locally hosted model as the decision-making layer.

  Source: README

• Keyless and offline operation — A connected local coding agent can be used without a new API key, while supported local model servers provide an offline path for missions and tool calling.

  Source: README

• Reproducible claims — Benchmark verdicts and headline claims are recomputed from committed artifacts, providing a receipt-based way to inspect reported results.

  Source: README

• Multiple security domains — The framework organizes specialist workflows for web applications, CTFs, source code, embedded and robotics systems, smart contracts, cloud infrastructure, mobile applications, and binary analysis. Its feature status distinguishes shipped capabilities from experimental and planned modules.

  Source: README, FEATURES.md

• Authorization and scope controls — The project is intended for authorized testing, research, and education. Built-in networked tools can refuse out-of-scope public hosts once a mission target is established.

  Source: README

Quick start

Copied verbatim from the project's README.

npm install
npm run server        # War Room → http://127.0.0.1:3333/ui/

ollama serve && ollama pull llama3                          # or an OpenAI-compatible server
export TEMPEST_LOCAL_BASE_URL=http://localhost:11434/api    # LM Studio: http://localhost:1234/v1
export TEMPEST_LOCAL_MODEL=llama3
npm run build                                               # only needed from a git clone
npx tempest                                                 # → "Change default provider" → local

curl http://localhost:3333/api/health
curl http://localhost:3333/api/bounty/platforms

Who it may suit

This may suit authorized security researchers, CTF participants, and engineers who want to connect an existing coding agent or local model to structured reconnaissance and evidence collection workflows.

Topics to discuss

• Which local-agent integration produces the most dependable workflow for an authorized security range?

• How should the project represent the boundary between stable reconnaissance workflows and experimental swarm capabilities in its documentation?

• Which evidence artifacts would be most useful for independently reviewing an authorized mission report?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/elder-plinius/T3MP3ST#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.