#openai

Drop-in self-hosted LLM proxy that reversibly redacts PII before OpenAI, ChatGPT and Ollama calls, including inside tool-call arguments and multimodal content. OpenAI-compatible, zero telemetry.

Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-aware, author-independent, and shift-left: secure_prompt secures the prompt before code generation. The security MCP for vibe coding: 450 rules, 39 tools, CLI + doctor for Next.js, Supabase, Clerk, Stripe, Prisma, Hono & MCP.

Your prompts need tests too. Run prompts against real datasets, score outputs with LLM judges, version everything, and compare runs to see what got better.

Recommends the right AI model, platform, and settings for any prompt — grounded in public benchmarks and per-category ratings. BYO-key CLI, MCP server, and web app.

A powerful CLI for AI-powered chat, automation, and multi-platform integrations — terminal-native alternative to Claude Code & OpenClaw. Chat with your bots, automate workflows, and connect Telegram, Discord, Slack & more.

A lightweight, DSL-driven LLM gateway for routing, patching provider quirks, and normalizing APIs across channels

Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.

✨多agent实现全自动AI小说生成

Yet Another Agent SDK, CLI, Claw, Agent Platform

A library and SDK to redact sensitive content from GenAI/LLM telemetry (prompts, completions, tool arguments) before it reaches observability backends. Supports OpenTelemetry conventions.

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

🔧 Repair JSON！Solution for JSON Anomalies from LLMs.

Laravel-native client for Model Context Protocol (MCP) servers. Built by Redberry (Diamond-tier Laravel partner). Used by LarAgent and other frameworks to enable AI agent functionality.

The only agent that doesn’t lock you in. You have 60+ models, free tiers, local LLMs, Docker sandbox — your agent, your rules.

CLI and SDK to automate i18n translation across i18next, vue-i18n, next-intl, ngx-translate, XLIFF, YAML, and Flutter ARB, using OpenAI, Anthropic, Gemini, and DeepL.

A feature-full starting point for production agent applications on Tangle.

Open-source AI Agent platform — 80+ MCP tools, 7 channels (Slack/Discord/LINE/Telegram), Rust + Python. Self-hostable Claude/GPT alternative for production multi-LLM systems.

Local CLI validator for Codex plugin packages, skills, and MCP server bundles.

🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.

500+ pay-per-call web tools + skill packs for AI agents — every one tested, priced, and settled on-chain. Paid in USDC over x402 on 8 chains, or free via proof-of-work on the pure-CPU tools. Self-hostable, MCP-native, deterministic. Plus the open x402 index (Find / Route / Leaderboard).

Self-hosted AI agent for automation, messaging, tools, integrations, and device control.

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

fak — the Fused Agent Kernel: one Go binary for AI agent loops. Wrap Claude Code/Codex/Cursor, keep long sessions cache-efficient, route work per call, run local GGUF models, and adjudicate tool calls.

The open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.

该仓库未发布描述。

Build AI agent fleets. 3 lines, any backend, local or cloud. Effort-based model routing, 48 identities, knowledge graph memory, fleet orchestration.

Responses API ↔ Chat Completions translation bridge for Codex CLI

From-zero terminal coding agent: a key-holding OpenAI-compatible routing backend + a thin client with ~285 skills, MCP connectors, and ask/plan/auto modes. No build step.

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

OpenCode Plugin for supervised agentic software development on a Kanban board