- Munich, Germany
- https://ernstberger.xyz/
- @0xSerious
Stars
Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.
Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for L…
A Lean backend framework whose authorization safety is formally proven. The developer writes only a Cedar schema and policies; handlers are built on Supabase Auth and PostgreSQL.
ryanbr / noop
Forked from muftiarfan/noopOffline WHOOP companion — pair your strap over Bluetooth, keep all data on your own device. No cloud, no account, no subscription.
The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.
Framework for evaluating and improving agents
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
[USENIX Security '25] Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems
Agent Executor (AX) is Google's open agentic orchestration runtime
This repo accompanies the paper "The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management" presented at the Fourth Deep Learning for Code (D…
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verb…
Open source alternative to Semrush and Ahrefs
Run any Linux process in a secure, unprivileged sandbox using Landlock. Think firejail, but lightweight, user-friendly, and baked into the kernel.
An incremental parsing system for programming tools
Buttercup finds and patches software vulnerabilities
Build faster with an Agentic Workforce. Safe, secure, and compliant is now the default.
A simple HTTP proxy that fogs over naughty URLs
Framework-neutral control contract for AI agents: eight interception points, three verdicts, and a conformance kit.
Secure agents in seconds by running them in a sandbox.
Hunt down social media accounts by username across social networks
Reference parser and interpreter for the Dogwood policy language
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
Interactive Effect Visualizations