Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enforce egress in the kernel (eBPF/LSM, Linux). Deterministic, offline-first, boun…

Worked examples of the observed_effect v0 evidence contract: a bounded, recomputable observed-effect record and an independent consumer.

Local-first AI code provenance: line-level attribution, PR risk reports, policy checks, and tamper-evident audit trails for AI-assisted software.

Runnable demo: a CI gate that denies an agent's undeclared privileged tool action before it runs, with evidence in the Security tab. Built on assay.

Recipe, gate, and report layer for canonical Assay evidence artifacts: DSSE recipes, replayable digest-bound packs, CI gates.

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…

💫 Toolkit to help you get started with Spec-Driven Development

Review what an AI agent release changed at runtime (files, network, MCP tools), gate the PR, and report findings in code scanning. For AI platform and security teams.

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command li…

👨‍🚀 buzz, A small/lightweight statically typed scripting language

Appium MCP on Steroids!

Community contributions for hooks and reference providers in python

A place where you can find all the libraries that suit your Zig lang needs. ⭐️ Please star to support this work!

SafeSkill — scan AI tool skills for security risks and prompt injection

GitHub Action for Assay evidence artifacts: verify bundles, publish PR summaries, SARIF, and downloadable reports.

Confirm Quality and Eliminate Risk by Testing Cloud Apps in Production.

Deterministic LLM testing for CI. Record→Replay + policy-as-code to block risky merges (PII, schema drift, regressions, budget creep).

Immediate Zig GUI for Apps and Games

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

Minimal CLI coding agent by Mistral

Static cost analysis for LLM workloads. Catch budget overruns before they hit production — like Infracost, but for AI. Offline-first, single binary.

Official Python SDK for LogVault - Audit-Log-as-a-Service

Official Node.js/TypeScript SDK for LogVault - Audit-Log-as-a-Service

port langgraph to Go: Build resilient AI agents as graphs. 中文名：懒狗

Zig based cross compilation for C, C++, Rust and Go. No Docker.

VOAB Team App AI - Flutter application (Flutter)