Search

AI application development framework for stable structured outputs, observable actions, and durable workflows.

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

An agentic middleware for automated JSON validation and self-correction from LLM outputs.

AI coding assistant for the terminal with 30+ LLM providers

Catch LLM cost anti-patterns in your Python AI app before they hit prod — a local, static token-cost linter.

AI Agent security evaluation framework — automated red-teaming for LLM tool-call governance.

Quickly create RAG apps, Agents, and Unleash the full power of AI with Vector Vault

AI model: SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507

AI model: AI45Research/AgentDoG1.5-Qwen3.5-4B

Deterministic eval gates and reliability primitives for LLM pipelines

Trinity AI协作框架 — 基于决策者-规划者-执行者三层角色分离的人机协作系统。

Open-source desktop AI workspace for MCP tools, local files, browser automation, and provider-agnostic LLM workflows.

Full-stack testing for Tauri apps — DOM, IPC, Rust backend, and database from one test. 28 MCP tools. Zero production cost.

Universal extension manager for AI coding tools: detect tools, scan repos, install Agent Skills, sync and remove safely.

CARRIE AI - Complete Security Agent Ecosystem (12+ Tools)

Stock analysis extension for Pi Agent — lightweight market data tools + strategy skills

Hermes-first framework skill for turning goals, specs, plans, spikes, and reviews into executable DongFeng control packets

Any brain, any agent. Package an AI agent's brain — persona, MCP stack, skills, memory, config — into one open, signed bundle and install it into any framework (OpenClaw, Hermes, Claude Code) in one click.

Verifiable Codex + Claude + Gemini collaboration framework with source checks, mutual cross-audit, merge gates, HTTP and MCP adapters.

ICL (Imperative Context Language) is an open specification for governed AI agent execution in enterprise systems. It defines the event format for identity propagation, approval gating, rollback, and immutable audit — plus the cognitive trace that turns every deployment into labelled training data.