#ai-agents

MCP server for AI agent payments: pay-per-call APIs (search, scraping, data, compute, media, research) with no vendor keys and a spend ceiling on every call. Works in Cursor, Claude Code, Claude Desktop, and Codex.

Official Go SDK for Vengtoo — authorization client for Vengtoo cloud and local agent

Markdown → one .slides.html deck that edits itself in the browser. Ships agent skills.

Sandboxes for AI agents: TypeScript, Python, Go, Java and Ruby SDKs, the runtime CLI, an MCP server, and agent integrations. Firecracker microVMs.

Lightweight self-hosted workflow scheduler in a single Go binary — an open-source Airflow/Azkaban alternative. Embedded SQLite, DAGs (cron + dependencies + backfill), polyglot tasks (shell/Python/SQL/JAR/HTTP), web console, REST API, and a built-in MCP server for AI agents. Linux & macOS.

Review every Claude Code edit in Plannotator's diff UI before it lands on disk. A per-session PreToolUse hook.

A plan-file factory for Claude Code — and the console that watches it run. Engine: parallel headless workers in git worktrees, script-owned gates, unattended drive loop (TypeScript, zero deps). Console: live web observability over driven repos.

TypeScript SDK for agent spend governance around paid tool calls across MCP, LangGraph, OpenAI, Claude, and Gemini: spend authorization, evidence receipts, refunds, disputes, and settlement.

Your AI remembers what it did, proves it, and gets smarter every session

The safety gate between AI agents and your servers. An MCP server for structured, policy-checked, audited infrastructure operations.

No repository description published.

Go CLI that converts CLI agent session logs into shareable transcripts

No repository description published.

A comprehensive suite of protocols, meta-prompts, and orchestration tools designed to streamline software development workflows, project management, and team collaboration. Includes the VibeCode Protocol Suite with web interface, user manuals, and reusable templates for efficient development processes.

No repository description published.

Independent Go CLI for brandable business & domain names — multi-format output, domain filters, agent-friendly JSON. Unofficial Namelix backend adapter (not affiliated).

Agent-agnostic software development harness CLI — scaffold, phase orchestration, gate validation for any coding agent

A tiny, dependency-free taxonomy for AI agent tool-call failures: retry, re-prompt, or escalate — with model-ready hints.

Local skill manager for AI coding agents: keep one copy of each skill, symlink it into every agent, toggle it per agent.

The verified-brief organ for coding agents — cited, OSV-gated, injection-safe retrieval + package verification.

Local hybrid (vector + BM25) code search for AI coding agents — AST chunking, MiniLM embeddings on ONNX, Go call graph, MCP server. No external services.

282+ structured privacy & data protection skills for AI agents. GDPR, CCPA, EU AI Act, HIPAA, LGPD, PIPL, DPDP Act.

Turn failed build logs into cited evidence packets for Claude, Codex, CI, and humans - locally.

Cryptographically-authenticated, cross-machine agent-to-agent chat for Claude Code, over MCP

Official Go SDK for xShellz sandboxes — spawn a throwaway, kernel-isolated Linux box and run commands in it from your code. go get github.com/xshellz/xshellz-go

LYT™ — Link Your Think: federated markdown vaults — the storage architecture for AI-native knowledge work, AI-first by design. Mint vaults you own, weave meshes you share, forge Your Pod. Markdown-in-Git, YON-structured, never phones home. 7 npm packages under @younndai. Apache-2.0 · free forever · alpha. By YounndAI — younndai.com.

The Makefile of agent orchestration. Terminal agent coordination without the framework tax. No Python. No cloud. No magic. Just tmux, TOML, and a binary.

No repository description published.

Runtime action firewall for AI agents: the keyless Shield. Screens catastrophic tool calls (DROP TABLE, SSRF, secret exfil) in-process, no key. Watches by default; set the posture to enforce to block. MIT.

泱穹 Agent Harness 是一套用纯 Java 构建的企业级 AI Agent 运行时开发框架，ReAct 循环、六大范式、子代理编排、持久化执行、安全护栏、全链路可观测。