#agent

ai cli coding Harness

TypeScript types and JSON Schema for MCP server specifications

Опис репозиторію не опубліковано.

Visual Markdown review server with Codex skill, sidecar comments, and HTTP APIs

Peer Cash SDK: cash out Base USDC to fiat at the live market rate

AI protocol scanner — discover exposed MCP servers, A2A Agent Cards, and open LLM APIs in one command. 一条命令盘点 MCP、A2A Agent Card 和 LLM 开放接口暴露面。

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

P2P multi agent orchestration harness, universal automation system and IDE

Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.

Опис репозиторію не опубліковано.

Agent Doris CLI

23-tool MCP server for CVE & vulnerability intelligence. NVD, EPSS, CISA KEV, GitHub Advisory, OSV — unified in one server. Risk scoring, bulk triage, exploit search. 2 dependencies, runs with npx.

Опис репозиторію не опубліковано.

Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.

🐱🦞Manboster: Meet Your Personal AI Agent Manbo Lobster! Made with love by hand.

AIMail: the native email system for the AI age — purpose-built for human-agent and agent-agent collaboration.

Local agent-to-agent artifact exchange for LLM workflows via HTTP, CLI, and MCP.

License-normalized reference retrieval for creative tools and agents — search images, video, audio, and text across pluggable sources via TypeScript SDK or MCP.

small coding agent in go

微信读书 CLI / WeRead CLI: 基于官方支持 API，面向人类与 AI Agent 的书架、笔记、划线、书评、阅读统计和推荐工具。Official API-based WeRead command-line tool with Agent Skill support.

Linux运维监控工具，支持系统硬件信息，内存，CPU，温度，磁盘空间及IO，硬盘smart，GPU，防火墙，网络流量速率等监控，服务接口监测，大屏展示，拓扑图，端口监控，进程监控，docker监控，日志监控，文件防篡改，数据库监控，指令批量下发执行，web ssh，Linux面板(探针)，告警，SNMP监测，K8S，Redis，Nginx，Kafka，资产管理，计划任务，密码管理，工作笔记

Run a close-to-real Claude Code session programmatically via the Agent SDK and expose it to a host app as something it can embed, watch, and control. Runner + wire protocol + gateway + embeddable panel.

Опис репозиторію не опубліковано.

AI-powered task queue for OpenCode agents — schedule, retry, and manage batch jobs with SQLite

A small deterministic SQLite graph index and query library.

Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.

Connect agents across runtimes, frameworks, and teams.

Local memory + orchestration layer for custom LLM agents: SCOPE-style tactical/strategic memory over execution traces, Qdrant-backed, polyglot subprocess tools, agent-as-tool composition.

一个用于开发学习的纯净 Agent。 / A Agent.

Stage-gate framework that forces coding agents to follow real engineering SOP: spec -> tests -> implementation, with verifiable evidence required at every step. 13 language adapters, tool interception, HMAC-signed state.