
Boucle-framework
Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt…

Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing,…

Wire-level proxy firewall for AI agents that intercepts and gates SQL, Kubernetes, and HTTP traffic using HCL rules, with per-process tunnel…

Just-in-time API keys for AI agents - and any other process you route through it: the caller only ever sees a placeholder.

Open-source EDR for AI agents. Monitor processes, files, network, and behavior of autonomous AI agents.

Lightweight Agent Detection & Response (ADR) layer for AI agents — guards commands, files, and web requests. Part of Gen Agent Trust Hub.

This project aims to compare and evaluate the telemetry of various EDR products.

Open-source AI-powered Security Operations Center — alert fusion, purple-team drills, agent-assisted triage, MITRE ATT&CK investigation.…

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

Bazzite plus a TPM boot attestation layer. Work in progress: builds unverified, UKI mechanism unresolved. Spec: github.com/plunder707/attested-gaming

A Java Agent that disables Apache Log4J's JNDI Lookup to mitigate CVE-2021-44228 ("Log4Shell").

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal…

First public analysis of SoftLanding UEFI bootkit: Ring -2 implant, CVE-2025-7029, 240+ Gigabyte boards, GPU AI evasion, dual C2. YARA + Sigma +…

Single-host runtime-security dashboard on eBPF — Go agent + SvelteKit. Live process tree, network map, and rule-based alerts for plain Linux hosts.

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

Fawkes is a golang Mythic C2 Agent exclusively written by AI.

Security for the modern age of AI: defend against bad AI agents and malicious npm packages