v0.2.30
Armur-Ai/Pentest-Swarm-AIv0.2.30Sep 29, 2026by github-actions[bot]
Upgrading?
AI Summary
Focuses on creating a heterogeneous swarm with the integration of OpenRouter, allowing access to 400+ models. It introduces a cost-aware active corroboration engine and tier-weighted confidence gates to mitigate context poisoning.
Key Highlights
- Integration with OpenRouter provider for 400+ models.
- Per-role model mixture for OpenRouter to optimize performance.
- Cost-aware active corroboration engine (verify mode).
- Tier-weighted confidence gate against context poisoning.
- Omnigent agent manifest support for governance.
New Features
- OpenRouter provider integration
- Per-role model mixture
- Cost-aware active corroboration engine
- Tier-weighted confidence gate
- Omnigent agent manifest
Full Release Notes
## Pentest Swarm AI v0.2.30 Install via Homebrew: ``` brew install Armur-Ai/tap/pentestswarm ``` Install via AUR (once submitted): ``` yay -S pentestswarm-bin ``` Run via Docker (16 security tools pre-installed): ``` docker run --rm ghcr.io/armur-ai/pentestswarm:v0.2.30 scan example.com ``` ## Changelog ### Features * dfd362804818e1aec807cfb558bcefddf3efc663: feat(cli,config): wire OpenRouter through init, launcher, scan flags (@AkhilSharma90) * 5686417f2f336abbba178417245a47e0aa91ef8f: feat(engine): per-role model mixture for OpenRouter (@AkhilSharma90) * 246f401676261ed57acfe94d7704a12811c02e2a: feat(integrations): Omnigent agent manifest — Pentest Swarm as a governed agent (@AkhilSharma90) * 4903f0126d0d002af64414790ebed3c236ece843: feat(llm): add OpenRouter provider — 400+ models on one key (@AkhilSharma90) * 9ca0d5350ea331ad9ad9e82c20519311498be460: feat(swarm): cost-aware active corroboration engine (verify) (@AkhilSharma90) * 39099df9a4f2921d7e2536b21b2a72be454d4090: feat(swarm): tier-weighted confidence gate against context poisoning (@AkhilSharma90) * 93e42e25fe74c2381b10faf2d63cbaf6c877b771: feat(swarm): wire active corroboration into classifier→exploit handoff (@AkhilSharma90) ### Other * aecbbf4a0501d30231044dab104d276c6d671442: chore(release): 0.2.30 — heterogeneous swarm (@AkhilSharma90) --- Full source: github.com/Armur-Ai/Pentest-Swarm-AI
Related Repositories
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
The world’s fastest framework for building websites.
:cherry_blossom: A command-line fuzzy finder