#agent

Multi-provider CLI for image generation and editing with OpenAI, Fal, Vercel AI Gateway, and custom OpenAI-compatible models

Describe workflows. Share them. Run them.

Open-source data protection framework for AI agent workflows in n8n. Detects, tokenizes, and reversibly anonymizes sensitive data before it reaches your models.

High-performance distributed load balancer.

Official typescript implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.

🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.

Doc77 — Local document preview, management & AI agent. Markdown/PDF/Office preview, lightweight editing, MCP server with approval workflow, offline translation en↔zh, multilingual UI (English/中文). Open-source, cross-platform, zero-config.

The provider-agnostic AI toolkit for Python

该仓库未发布描述。

The open-source client-agnostic agent harness

🤖 Autonomous Multi-Agent AI Workspace in your terminal. Codes, researches, and executes real tasks with 40+ tools and 280+ skills And Some Captcha Resolver With Only Vision Mode Any Captcha And Opening A Browser And Full Control Of It

该仓库未发布描述。

Kimi Agent SDK provides a programmatic interface to interact with the Kimi CLI

Shared headless primitives for autonomous UX drivers (activity bus, effect dispatch, undo, presence) used by agent-integrations and fancy-flow's FlowRunnerUx.

A framework for giving any AI agent persistent, browser-trainable SSM memory — Mamba models, swappable LLM bridges, and online distillation. The hippocampus behind BuilderForce.ai.

A discovery layer for everything in the Stellar Ecosystem

MCP server + CLI that puts a real human in your coding agent's loop. It publishes work mid-task, a reviewer pins what's wrong and returns a verdict, and the agent iterates until approved.

workflow agent watchdog to ensure delivery using async / distributed-systems building blocks

A cross-agent CLI your coding agent uses to delegate work. It gets back an answer, a review, or a patch — not the delegate's working context.

Auto-model router middleware for the pi coding agent — routes each LLM request across local, economical cloud, and frontier tiers with session pinning and cache-aware economics.

该仓库未发布描述。

Stateful, structured, safe command execution for AI agents - over local shells, SSH, and Docker.

用最少的代码复刻 OpenClaw 的 agent 运行原理

Fast and powerful templates. Valid markdown. Strongly typed and great for agents. Supports Rust, Python, Go, TypeScript

该仓库未发布描述。

Inspired by the idea of the Upside Down, Downcity is a parallel city built for agents — a hidden operating layer beneath the surface. It is where agents are organized, coordinated, and put to work.

AI agent that lives in your chat apps. Controls your machine, remembers your conversations, searches your documents — with guardrails so it doesn't go rogue. OpenClaw without the bloat

该仓库未发布描述。

该仓库未发布描述。