Search

Give AI coding agents case-by-case sudo access via GUI approval, with SSH-key-encrypted password storage

1282 production-ready AI agent skills with self-evolving meta-skills — cybersecurity, SEO, trading, marketing, automation, devops, content, financial services

AI tool hook adapter for punkgo-kernel — every tool call gets a cryptographic receipt

Enterprise tool for discovering AI Agents running within an organization

Public Preview — Episodic Memory Kernel for AI agent experience storage

Evidence-first agentic CTF runtime for Kali Linux — build and field your own AI CTF experts

Client and CLI for Attested Memory: write, search and read verifiable AI-agent memory under a signed Ed25519 actor identity.

Gate LangChain tool calls behind a signed Fidacy verdict. Wraps the tool itself, so a denied payment never executes: callbacks can only observe, this can stop.

A CodeQL tool to automatically execute code scanning.

eBPF-based System Inspector and Forensic Tool (Multi-Agent/Web)

Run AI coding agents (Claude Code, OpenCode) safely inside sandboxed Docker containers with audit logging

A penetration testing agent powered by local LLMs via Ollama

Public Preview — Agent Hypervisor: Runtime supervisor for multi-agent Shared Sessions with Execution Rings, Joint Liability, Saga Orchestration, and hash-chained audit trails

Governance patterns for autonomous AI agents at SEC-registered investment advisers (private capital)

A fail-closed, fully-local, no-account in-loop verifier for AI-written code: deterministic checks the instant your agent writes, and it never claims 'safe'.

Production-hardened Python redaction for structured logs, LLM agent payloads, and AWS-signed URLs.

Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude Code and OpenAI Codex.

PikaKit — AI Operating System. 51 skills, 18 workflows, strict TypeScript.

AI model: AI45Research/AgentDoG-FG-Llama3.1-8B (text-classification)

A least-privilege controller for local coding agents