Search

透明可审计的本地智能体终端：对开源 agent 框架做安全审计与加固（RCE/沙盒绕过/注入），并以 50 条注入基准 × 37 条能力基准双维度量安全边界

An interactive, client-side app that teaches how modern agents and language models work and how they are used.

海龟汤（情境猜谜/横向思维谜题）创作方法论——四阶段施工框架 | A methodology for crafting turtle soup / lateral thinking puzzles: 4-phase pipeline from embryo to finished puzzle (CC BY-NC 4.0)

Record what your coding agent did, derive guards from it, enforce them, and verify each run stayed in scope. Claude Code and OpenAI Codex.

LLM-assisted Playwright Page Object Model generator with live locator verification.

Pytest plugin: recorded agent sessions (JSONL) as deterministic tool-call assertions. No LLM.

DSH 智能上下文压缩插件 —— 在有限窗口内管理认知资源，让 Agent 记住真正重要的信息。 Smart context compression for DSH — managing cognitive resources within limited windows, so your Agent remembers what truly matters.

Govern any AI agent in 3 lines. Ships in shadow mode — drop it into your LangChain/CrewAI/LangGraph loop and see what /admit would have blocked. Zero dependencies.

Pre-purchase seller evidence, policy authorization, and receipt primitives for AI agents buying APIs through x402 or MPP

Sync AI agent configurations (skills, agents, prompts) from shared sources into your project's tool directories.

Tell Neuvikon which ticket your coding agent is working on.

Secure AI Agent Sandbox with Docker & eBPF interceptors

Find AI-agent cost risks in your code — uncapped LangGraph loops, missing caps, and LLM call-site costs. Local, no signup, MIT.

A minimal CLI agent

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...

Shared CLI conventions for agent-facing tools: exit codes, JSON output, skill installation, and the in-binary guide.

Runtime governance middleware for CrewAI: exit reports, overlap detection, knowledge inheritance.

Unified interfaces, wrappers, and vector environments for multi-agent reinforcement learning.

Coverage-guided fuzzing taskflow for the GitHub Security Lab Taskflow Agent (https://github.com/GitHubSecurityLab/seclab-taskflow-agent)