541.90K
total weekly downloads
54 packages
@agent-sh/agent-workspace-linux
Background Linux desktops for AI agents: the MCP server binary wrapper.
@agent-sh/chrome-bridge
Let Claude Code, Codex and other MCP agents drive your real Chrome: your tabs, logins and profile, via an extension, native messaging and one shared MCP server.
@agent-sh/computer-use-linux
Native Linux desktop control for AI agents (MCP server, Pi tools, and CLI): semantic AT-SPI accessibility trees, screenshots, compositor window targeting, Wayland/X11 input, and an on-screen activity indicator.
@agent-sh/harness-bash
Bash tool for AI agent harnesses — autonomous shell execution with pluggable executor, permission hook, cwd-carry, inactivity timeout, and background job support
@agent-sh/harness-batch
Batch tool for AI agent harnesses — execute commands across multiple directories with glob, subdirs, or explicit targets; sequential or parallel execution; fail-fast; summary or detailed output
@agent-sh/harness-core
Shared types, permissions, ledger, cache, and LLM tool-adapter emitters for @agent-sh/harness-* tools
@agent-sh/harness-glob
Glob tool for AI agent harnesses — ripgrep-backed filename pattern search with structured output, pagination, .gitignore respect, and mtime sort
@agent-sh/harness-grep
Grep tool for AI agent harnesses — ripgrep-backed content search with structured output modes, pagination, .gitignore respect, and a WASM-bundled engine
@agent-sh/harness-lsp
LSP tool for AI agent harnesses — language-server-protocol operations (hover, definition, references, symbols) with .lsp.json manifest, lazy-spawn policy, and pluggable LspClient adapter
@agent-sh/harness-read
Read tool for AI agent harnesses — safe, bounded, line-numbered file reading with pluggable I/O, permissions, ledger, and cache
@agent-sh/harness-skill
Skill tool for AI agent harnesses — authored SKILL.md activation with progressive disclosure, permission-gated activation, trust-gated project skills, and pluggable SkillRegistry
@agent-sh/harness-tools
Umbrella package and PI extension for @agent-sh/harness-* agent tools (read, write, grep, glob, bash, webfetch, websearch, lsp, skill)
@agent-sh/harness-webfetch
WebFetch tool for AI agent harnesses — HTTP GET/POST with SSRF defense, readability+markdown extraction, redirect-chain reporting, size caps, and per-session cache
@agent-sh/harness-web-mcp
MCP stdio server exposing @agent-sh/harness-websearch and @agent-sh/harness-webfetch to Claude Code, Codex and any MCP client: keyless web search plus SSRF-safe fetch with markdown extraction
@agent-sh/harness-websearch
WebSearch tool for AI agent harnesses: zero-config keyless web search (Exa/Parallel/Mojeek/Marginalia/Wikipedia fallback chain) with optional Brave/Tavily/SearXNG backends, SSRF defense, declarative query controls, result-count cap, and a discriminated re
@agent-sh/harness-write
Write / Edit / MultiEdit tools for AI agent harnesses — ledger-anchored, atomic, with structured fuzzy diagnostics
@agent-sh/parlar
Voice conversation mode for Claude Code and Codex: talk to a running session and it answers out loud while it works.
@agent-sh/tower-crane
Plan, dispatch, review and merge agent work from one issue to a whole project, with state in one SQLite file and gates in software
agentsys
A modular runtime and orchestration system for AI agents - works with Claude Code, OpenCode, and Codex CLI
agnix
Linter for AI agent configurations. Validates SKILL.md, CLAUDE.md, hooks, MCP, and more.
awesome-slash
12 specialized plugins for AI workflow automation (drift detection + AST repo maps + topic research + agent config linting) - works with Claude Code, OpenCode, and Codex CLI
awsome-slash
Professional-grade slash commands for Claude Code that work across any project
error-fortune-cookies
Transform boring error messages into hilarious fortune cookie wisdom
ferrings
Linux io_uring TCP transport for Node.js services
ferrings-linux-arm64-gnu
Native ferrings binding for linux-arm64-gnu