Lists (5)
Stars
Open-source AI cybersecurity harness. Build & deploy continuous security agents that find, prove, fix and monitor vulnerabilities across code, binaries, dependencies, infrastruc 8000 ture and AI agents. …
Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh
Agent Skills that teach coding agents to write, review, and port idiomatic Rust, plus a tested clippy config. Works with Claude Code, Codex, Copilot, Cursor, and Gemini CLI.
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
Use Claude Code, Codex, Antigravity, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native brows…
Omarchy 4.x vendored for NixOS — the upstream tree packaged as a derivation, not reimplemented in Nix
Review-first terminal diff viewer for agentic coders
LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and m…
DeepSeek Harness: Everything is a Plugin.
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C infe…
High performance coding agent harness written in Rust, built for heavy multi-agent dev workflows
MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts
Onboard AI tools in one step, and catch the rest. Relay sets up Claude Desktop, Claude Code, and Codex to run through your LiteLLM AI Gateway with zero dev setup and routes shadow AI (Notion AI, Pe…
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
Library and command-line utility for rendering projects templates.
Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild
Your agent team, in one group chat.
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.