#agent

该仓库未发布描述。

In-VM exec agent for Cocoon: vsock-based command execution channel that replaces SSH for kubectl exec on Cocoon-managed VMs.

Serve any Streamlit app as an MCP server — agents drive it natively, no browser automation.

Plan/apply for your GTM stack — canonical CRM data model, deterministic audits, reviewable patch plans, approval-gated writeback. Think terraform plan for your CRM.

One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.

A Sui-native, policy-bound, non-custodial AI finance agent. Natural-language goals → policy-checked PTBs, executed only within approved on-chain scope, with auditable Walrus receipts.

Provider-agnostic TypeScript agent SDK — pluggable providers, built-in tools, skills, memory, and MCP

A high-performance, ultra-lightweight Go implementation of the AI Agent, inspired by Nous Research’s hermes-agent.

AI venture studio: mines your support tickets and issues for opportunities, sizes markets honestly, writes PRDs with kill criteria, builds and reviews the product from one plain-language doc (English/中文), measures real cohorts, and forces honest kill decisions. Humans hold every gate; it never publishes or spends.

该仓库未发布描述。

AI native API/MCP framework for the agent era. Built with agents, for agents.

Reusable Go runtime packages for building and configuring ACP-backed agents

A CLI tool for everything that is needed in a day to day software development basis

Make agent context work on every try. Context engineering toolkit for coding agents (Claude, Cursor, Codex, Copilot, Grok).

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.

Detect if your application is being invoked by an AI coding agent such as Claude Code, Copilot, Cursor, Codex, Aider, and many more.

A Go SDK for the Claude Code CLI: one-shot runs, interactive sessions, in-process Go tools, permission & hook callbacks, inline subagents. Behaviorally verified against the real binary.

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

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.

OpenCode TUI 插件 · 实时子代理监控 · 侧边栏可视化 / Real-time Sub-Agent Monitor Sidebar Plugin for OpenCode TUI

A unified AI desktop assistant and agentic CLI with screen vision, automation, local memory, and multi-provider intelligence.

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.

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.

Project VoidRift: Local-first Agentic Development Framework

Agent Action Capsule — an open SCITT statement profile for recording and verifying what an AI agent did (draft-mih-scitt-agent-action-capsule)

A Model Context Protocol server that provides AI agents with tools to read and write Jira Cloud data.

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.

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

该仓库未发布描述。

Slack CLI for power users