#openai

The authorization kernel for AI agents. Block, allow, or escalate agent tool calls with YAML rules — deterministic-first, LLM fallback.

Open agentic runtime in TypeScript — run any coding agent in the background, check its work before it lands, and project tools/skills/agents/workflows into CLI, HTTP, MCP, SDK, Mastra & the AI SDK.

An AI SDK for building agents and tools in Laravel applications

A governed agent SDK for TypeScript - cost budgets, tamper-evident audit, and PII redaction built into the loop.

Scala client for OpenAI API and other major LLM providers

LLM Simulation for Load Testing

Modular Python library for unified LLM provider access with cost reporting

Get a saved, cited report from your AI agent

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.

Minimal CLI agent framework with compounding project memory — gets smarter with every session. Clean, modular, any LLM provider

Rust library wrapping 12 AI CLI tools as pluggable LLM providers — with OpenAI API client, ACP headless mode, agent loop, MCP server, and OpenAI-compatible REST API

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.

Improve Pi prompt/KV cache hit rates with stable prompts, OpenAI-compatible cache keys, proxy compat warnings, and footer cache stats.

Validate and retry LLM outputs for ruby_llm. Describe the JSON response you expect, fall back to a stronger model when the cheaper one fails the rules, and gate CI on regressions — all as one contract object per step.

tbls-ask is an external subcommand of tbls for asking LLM of the datasource.

Framework-agnostic PHP SDK for AI providers with typed results and platform abstraction

Reach your local model server from anywhere — p2p, end-to-end encrypted, no VPN, no account, no cloud in the path

AI multimodal CLI — Gemini, MiniMax, OpenRouter, ffmpeg, ImageMagick, doc-to-md

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.

Use OpenAI Responses API native compaction in OpenCode

Orchestration of autonomous, collaborative AI agents in Go — an idiomatic Go port of CrewAI.

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

Auto-translate i18n locale files with AI. Translate i18next JSON, Gettext PO, Java .properties, iOS .strings, Rails YAML, and TS/JS catalogues using ChatGPT, Claude, Gemini, or local Ollama models. CLI, Node library, and GitHub Action.

A translator's kit that uses the free APIs of Google Translate, Yandex, Bing, ChatGPT, and other LLMs

Token-Oriented Object Notation - A compact data format for reducing token consumption when sending structured data to LLMs (PHP implementation)

Local‑first MCP server for multi‑repository semantic code search with Qdrant and llama. Turns your entire workspace into private context for AI coding assistants like Claude Code, Codex, Cursor, Copilot, Antigravity and Windsurf.

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

Multi-tier AI orchestration CLI — built for developers who think in systems.

Small polyglot cost ledger for LLM and agent API calls

Power Claude Code, Codex CLI, and more with your Copilot subscription.