Practical overview
When it fits
Use Redcell when an authorized, scoped assessment benefits from autonomous task coordination, real tool execution in Kali, interactive operator control and structured reporting.
Who it is for
- Security teams conducting authorized penetration tests
- Researchers working on controlled red-team workflows
- Operators who need live oversight of agent activity and findings
Documented uses
- Coordinate planning and execution across LLM security agents
- Run documented security tools and record hosts, findings and attack-surface data
- Drive browser-based testing for login flows and JavaScript-heavy applications
- Review, verify, dismiss and merge findings
- Export assessment results for human and machine-readable workflows
Requirements & limits
The repository is public and identified as MIT-licensed. The documented quickstart requires Docker, uv and bun. The project warning restricts use to education, research and legal, authorized security testing within an agreed scope.
- Execution is performed in a Kali container, locally or through a saved remote server over SSH.
- The console supports live agent activity, browser streaming, terminals and operator interaction.
- Dedicated tools include nmap, nuclei, directory and virtual-host discovery, and Metasploit search and run; run_command covers other commands.
- Network pivoting can route tool traffic through a caught reverse shell using a chisel reverse SOCKS tunnel.
- Findings can be triaged before reports are generated.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up Redcell’s development environment
Start the documented local infrastructure, dependencies, database and seed data.
Before you start
- Docker
- uv
- bun
Steps
Start Postgres, Redis and MinIO with docker compose -f docker-compose.dev.yml up -d.
Install the live Python dependencies with uv sync --group live.
Apply database migrations with uv run rc db upgrade.
Seed the admin user, provider catalog and buckets with uv run rc seed.
Copy the environment template with cp .env.example .env.
Expected outcome
The documented local infrastructure and initial application data are prepared, with an environment file copied for configuration.
Guide limitations
- These steps cover setup only; the supplied documentation does not provide the remaining configuration or execution steps.
- The repository warning requires testing only systems owned by the operator or covered by explicit written permission and an agreed scope.
Compare options for Agent orchestration
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Redcell | Coordinate planning and execution across LLM security agents | Cloud, Docker, Linux, Server | The repository is public and identified as MIT-licensed. The documented quickstart requires Docker, uv and bun. The project warning restricts use to education, research and legal, authorized security testing within an agreed scope. |
| Threatswarm | Coordinate reconnaissance through reporting in one assessment session | CLI, Desktop, Self-hosted | The repository is public, active and MIT-licensed. The documented access paths use Claude Code with either a marketplace installation, a cloned repository or the --plugin-dir option. No pricing or account requirement is provided. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 30 September 2026
- Original website title
- martian56/redcell · Official homepage title · retained in its source language